SlideShare uma empresa Scribd logo
1 de 40
Abstract NLP UGPP CI References
Parallelization of
Benchmarking using HPC:
Text Summarization in Natural Language Processing
(NLP), Glider Piloting in Deep-sea Missions, and
Search Algorithms in Computational Intelligence (CI)
ASHPC21, Austrian-Slovenian High-Performance Computing Meeting
Institute of Information Science in Maribor, Slovenia
1 May – 2 June, 2021 (online exclusively via livestream)
Aleš Zamuda
ales.zamuda@um.si
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 1/ 40
Abstract NLP UGPP CI References
Introduction: Overview
This contribution focuses on
I recent developments and trends
I in terms of efficient and successful
I high-performance computing (HPC) applications.
Real examples: science and HPC
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 2/ 40
Abstract NLP UGPP CI References
Introduction: Aims of this Talk at ASHPC21 Meeting
I First (5 minutes), a collaboration benefiting from HPC:
a state-of-the-art topic of text summarization for NLP
(part of ”Big Data”),
I spanning over the time curse of successful HPC initiatives
including Slovenia: SLING → SIHPC → ImAppNIO →
cHiPSet → HPC RIVR → TFoB → EuroCC → DAPHNE
I Second (+10 minutes), additional success stories are listed,
like those developed through program funded unit P2-0041,
HPC RIVR project, and projects by EU under programs like
Erasmus+, COST (Cooperation in Science and Technology)
and H2020 (Horizon 2020).
I Third (5 minutes), this contribution aims at leveraging
potential opportunities in NLP and HPC for shared and
collaborative synergies, enhancing sustainable HPC
development.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 3/ 40
Abstract NLP UGPP CI References
HPC Application 1:
Text Summarization
I NLP and computational linguistics for Text Summarization:
I Multi-Document Text Summarization is a hard CI challenge.
I Basically, an evolutionary algorithm is applied for
summarization,
I it is a state-of-the-art topic of text summarization for NLP
(part of ”Big Data”) and presented as a collaboration
[JoCS2020], acknowledging several efforts.
I we add: self-adaptation of optimization control parameters;
analysis through benchmarking using HPC, and
apply additional NLP tools.
I How it works: for the abstract, sentences from original text
are selected for full inclusion (extraction).
I To extract a combination of sentences:
I can be computationally demanding,
I we use heuristic optimization,
I the time to run optimization can be limited.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 4/ 40
Abstract NLP UGPP CI References
1 – Preprocessing (environment sensing, knowledge
representation) (1/2)
1) The files of documents are each taken through the following
process using NLP (Natural Language Processing) tools:
INPUT
CORPUS
NATURAL
LANGUAGE
PROCESSING
ANALYSIS
CONCEPTS
DISTRIBUTION
PER
SENTENCES
MATRIX OF
CONCEPTS
PROCESSING
CORPUS
PREPROCESSING
PHASE
OPTIMIZATION
TASKS
EXECUTION
PHASE
ASSEMBLE
TASK
DESCRIPTION
SUBMIT
TASKS
TO PARALLEL
EXECUTION
OPTIMIZER
+
TASK DATA
ROUGE
EVALUATION
2) For each document is D, sentences are indexed using NLP tools.
I Terms across sentences are determined using a semantic analysis
using both:
I coreference resolution (using WordNet) and
I a Concept Matrix (from Freeling).
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 5/ 40
Abstract NLP UGPP CI References
1 – Preprocessing (environment sensing, knowledge
representation) (2/2)
I 3) For each i-th term (wi ), during indexing
I number of occurences in the text is gathered, and
I number of occurences (nk ) of a term in some k-th statement,
I 4) For each term wi in the document, inverse frequency:
isfw i = log(
n
nk
),
I where n denotes number of statements in the document, and
I nk number of statements including a term wi .
I 5) To conclude preprocessing, for each term in the document,
a weight is calculated:
wi,k = tfi,kisfk,
where tfik is number of occurences (term frequency) of a term
wk in a statement si .
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 6/ 40
Abstract NLP UGPP CI References
2 – Summary Optimization (1/3)
I Sentence combination (X) is optimized using jDE algorithm:
I as a 0/1 knapsack problem, we want to include optimal
selection of statements in the final output
I an i-th sentence si is selected (xi = 1) or unselected (xi = 0).
I a) Price of a knapsack (its fitness) should be maximized,
I the fitness represents a ratio between content coverage, V (X),
and redundancy, R(X):
f (X) =
V (X)
R(X)
,
I considering a constraint: the summary length is L ±  words.
I Constraint handling with solutions:
I each feasable solution is better than unfeasable,
I unfeasable compared by constraint value (lower better),
I feasable compared by fitness (higher better).
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 7/ 40
Abstract NLP UGPP CI References
2 – Summary Optimization (2/3)
I b) Content coverage V (X) is computed as a double sum of
similarities (defined at d)):
V (X) =
n−1
X
i=1
n
X
j=i+1
(sim(si , O) + sim(sj , O))xi,j ,
I where xi,j denotes inclusion of both statement, si , and sj ,
I xi,j is only 1 if xi = xj = 1, otherwise 0,
I and O is a vector of average term weights wi,k :
O = (o1, o2, ..., om) for all i = {1..m} different text terms:
oi =
Pn
j=1 wi,j
n
.
I c) Redundance R(X) is also measured as double similarity
(defined at d)) sum for all statements:
R(X) =
n−1
X
i=1
n
X
j=i+1
sim(si , sj )xi,j ,
I where xi,j denotes inclusion of both statement, si , and sj ,
I again, xi,j is only 1 if xi = xj = 1, otherwise 0.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 8/ 40
Abstract NLP UGPP CI References
2 – Summary Optimization (3/3)
I d) Similarity between statements si = [wi,1, wi,2, ..., wi,m] and
sj = [wj,1, wj,2, ..., wj,m] is computed:
sim(si , sj ) =
m
X
k=1
wi,kwj,k
pPm
k=1 wi,kwi,k
Pm
k=1 wj,kwj,k
,
where wi,k is term weight (defined in 5)) and m number of all
terms in text.
I e) When concluded:
I the selected statements from the best assessed combination
are printed,
I in order as they appear in the text, and
I the summary is stored.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 9/ 40
Abstract NLP UGPP CI References
Summary Optimization — Algorithm Pseudocode
The detailed new method called
CaBiSDETS is developed in the
HPC approach comprising of:
I a version of evolutionary
algorithm (Differential
Evolution, DE),
I self-adaptation, binarization,
constraint adjusting, and
some more pre-computation,
I optimizing the inputs to
define the summarization
optimization model.
Aleš Zamuda, Elena Lloret.
Optimizing Data-Driven Models
for Summarization as Parallel
Tasks. Journal of Computational
Science, 2020, vol. 42, pp. 101101.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 10/ 40
Abstract NLP UGPP CI References
Running the Tasks on HPC: ARC Job Preparation 
Submission, Results Retrieval  Merging [JoCS2020]
Through an HPC approach and by parallelization of tasks,
a data-driven summarization model optimization yields
improved benchmark metric results (drawn using gnuplot merge).
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 11/ 40
Abstract NLP UGPP CI References
Results Published in Journal of Computational Science
The most interesting finding of the HPC study though is that
I the fitness of the NLP model keeps increasing with prolonging
the dedicated HPC resources (see below) and that
I the fitness improvement correlates with ROUGE evaluation in
the benchmark, i.e. better summaries.
-0.05
0
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0.4
1 10 100 1000 10000
ROUGE-1R
ROUGE-2R
ROUGE-LR
ROUGE-SU4R
Fitness (scaled)
Hence, the use of HPC significantly contributes to capability of
this NLP challenge.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 12/ 40
Abstract NLP UGPP CI References
HPC Application 2:
Underwater Glider: Autonomous, Unmanned, Robotic
I underwater glider – navigating sea oceans,
I Autonomous Underwater Vehicle (AUV)
6=
Unmanned Aerial Vehicle (UAV)
I AUV Slocum model (expertise in domain of ULPGC, work
with J. D. Hernández Sosa)
Images:
”Photo: Richard Watt/MOD” (License: OGL v1.0)
Slocum-Glider-Auvpicture 5.jpg (License: Public Domain)
MiniU.jpg (License: CC-BY-SA 3.0)
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 13/ 40
Abstract NLP UGPP CI References
The Buoyancy Drive and Submarine Probes Usefulness
I Driving ”yoyo” uses little energy, most only on descent and
rise (pump); also for maintaining direction little power is
consumed.
+ Use: improving ocean models with real data,
+ the real data at the point of capture,
+ sampling flow of oil discharges,
+ monitoring cable lines, and
+ real-time monitoring of different
sensor data.
1
http://spectrum.ieee.org/image/1523708
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 14/ 40
Abstract NLP UGPP CI References
Preparations – Simulation Scenarios
https://www.google.si/maps/@28.059806,-15.998355,650054m/data=!3m1!1e3
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 15/ 40
Abstract NLP UGPP CI References
Trajectory Optimization: P201,ESTOC2013 3
+ BigData, MyOcean IBI,
satelite link, GPS location
The real trajectory and collected data is available in a Google Earth KML file at the EGO network:
http://www.ego-network.org/dokuwiki/doku.php?glider=P201,ESTOC2013_3
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 16/ 40
Abstract NLP UGPP CI References
Constrained Differential Evolution Optimization
for Underwater Glider Path Planning
in Sub-mesoscale Eddy Sampling
I Corridor-constrained optimization:
eddy border region sampling
I new challenge for UGPP  DE
I Feasible path area is constrained
I trajectory in corridor around the
border of an ocean eddy
The objective of the glider here is to
sample the oceanographic variables more
efficiently,
while keeping a bounded trajectory
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 17/ 40
Abstract NLP UGPP CI References
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 18/ 40
Abstract NLP UGPP CI References
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 19/ 40
Abstract NLP UGPP CI References
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 20/ 40
Abstract NLP UGPP CI References
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 21/ 40
Abstract NLP UGPP CI References
HoP — New Trajectories:
Success history applied to expert system for underwater
glider path planning using differential evolution
I Improved underwater glider path
planning mission scenarios:
optimization with L-SHADE.
I Several configured algorithms
are also compared to, analysed,
and further improved.
I Outranked all other previous
results from literature and
ranked first in comparison.
I New algorithm yielded
practically stable and
competitive output trajectories.
I UGPP unconstrained scenarios —
contributed significantly to the capacity of
the decision-makers for mission plannings.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 22/ 40
Abstract NLP UGPP CI References
Ranking UGPP —
Benchmarking
Aggregation
I Statistically,
all results
from previous paper
were outperformed.
I Main reasons:
tuning (NP),
parameter control
(L-SHADE).
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 23/ 40
Abstract NLP UGPP CI References
HPC Application 3:
Multi-application domain generalized
Computational Intelligence (CI) through HPC
I With the ubiquity of HPC and Cloud Computing,
I connectible using versatile interfaces for their utilisation,
I example successes of these systems is computational
intelligence.
I One of designs for these services is:
I using evolutionary optimization approaches,
I needing much efficiently parallelizable data processing power.
I There are several application domains of this approach:
I generalized numerical functions problems and
I other parallel real world problems, such as
I text processing,
I molecular modelling,
I evolutionary computer vision, and
I robotics.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 24/ 40
Abstract NLP UGPP CI References
CI Algorithm Design: Control Parameters Self-Adaptation
I Through more suitable values of control parameters the search
process exhibits a better convergence (CI — Computational
Intelligence),
I therefore the search converges faster to better solutions,
which survive with greater probability and they create more
offspring and propagate their control parameters
I Recent study with cca. 10 million runs of SPSRDEMMS:
A. Zamuda, J. Brest. Self-adaptive control parameters’
randomization frequency and propagations in differential
evolution. Swarm and Evolutionary Computation, 2015, vol.
25C, pp. 72-99.
DOI 10.1016/j.swevo.2015.10.007.
– SWEVO 2015 RAMONA / SNIP 5.220
I Deployed using arcsub.
I Update: DISH algorithm —
https://doi.org/10.1016/j.swevo.2018.10.013
(Outperforms on CEC 2017 functions.)
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 25/ 40
Abstract NLP UGPP CI References
Existing Challenges: Benchmarks for Known Environments
Inspired by previous computational optimization competitions in continuous settings
that used test functions for optimization application domains:
I single-objective: CEC 2005, 2013, 2014, 2015
I constrained: CEC 2006, CEC 2007, CEC 2010
I multi-modal: CEC 2010, SWEVO 2016
I black-box (target value): BBOB 2009, COCO 2016
I noisy optimization: BBOB 2009
I large-scale: CEC 2008, CEC 2010
I dynamic: CEC 2009, CEC 2014
I real-world: CEC 2011
I computationally expensive: CEC 2013, CEC 2015
I learning-based: CEC 2015
I 100-digit (50% targets): 2019 joined CEC, SEMCCO, GECCO
I multi-objective: CEC 2002, CEC 2007, CEC 2009, CEC 2014
I bi-objective: CEC 2008
I many objective: CEC 2018
Tuning/ranking/hyperheuristics use. → DEs as usual winner algorithms.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 26/ 40
Abstract NLP UGPP CI References
IEEE Congress on Evolutionary Computation (CEC)
Competitions (1/4)
I Storn, Rainer, and Kenneth V. Price. ”Minimizing the Real Functions of
the ICEC’96 Contest by Differential Evolution.”
International Conference on Evolutionary Computation. 1996.
I ...
I CEC 2005 Special Session / Competition on
Evolutionary Real Parameter single objective optimization
I CEC 2006 Special Session / Competition on
Evolutionary Constrained Real Parameter single objective optimization
I CEC 2007 Special Session / Competition on
Performance Assessment of real-parameter MOEAs
I CEC 2008 Special Session / Competition on
large scale single objective global optimization with bound constraints
I CEC 2008 Scale-Invariant Optimisation Competition ”Mountains or Molehills”
I CEC 2009 Special Session / Competition on
Dynamic Optimization (Primarily composition functions were used)
I CEC 2009 Special Session / Competition on
Performance Assessment of real-parameter MOEAs
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 27/ 40
Abstract NLP UGPP CI References
IEEE Congress on Evolutionary Computation (CEC)
Competitions (2/4)
I CEC 2010 Special Session / Competition on
large-scale single objective global optimization with bound constraints
I CEC 2010 Special Session / Competition on
Evolutionary Constrained Real Parameter single objective optimization
I CEC 2010 Special Session on
Niching Introduces novel scalable test problems
I CEC 2011 Competition on Testing Evolutionary Algorithms on Real-world
Numerical Optimization Problems
I CEC 2013 Special Session / Competition on
Real Parameter Single Objective Optimization
I CEC 2014 Special Session / Competition on
Real Parameter Single Objective Optimization
(incorporates expensive functions)
I CEC 2014: Dynamic MOEA Benchmark Problems
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 28/ 40
Abstract NLP UGPP CI References
IEEE Congress on Evolutionary Computation (CEC)
Competitions (3/4)
I CEC 2015 Special Session / Competition on
Real Parameter Single Objective Optimization (incorporates 3 scenarios)
I CEC 2015 Black Box Optimization Competition
I CEC 2015 Dynamic Multi-Objective Optimization
I CEC 2015 Optimization of Big Data
I CEC 2015 Large Scale Global Optimization
I CEC 2015 Bound Constrained Single-Objective Numerical Optimization
I CEC 2015
Optimisation of Problems with Multiple Interdependent Components
I CEC 2015 Niching Methods for Multimodal Optimization
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 29/ 40
Abstract NLP UGPP CI References
IEEE Congress on Evolutionary Computation (CEC)
Competitions (4/4)
I CEC 2016 Special Session / Competition on
Real Parameter Single Objective Optimization (incorporates 4 scenarios)
I CEC 2016 Big Optimization (BigOpt2016)
I CEC 2016 Niching Methods for Multimodal Optimization
I CEC 2016 Special Session Associated with Competition on
Bound Constrained Single Objective Numerical Optimization
I CEC2017 Special Session / Competition on Real Parameter Single
Objective Optimization (also constrained)
I CEC2018 Special Session / Competition on Real Parameter Single
Objective Optimization
I CEC2019 Special Session / Competition on 100-Digit Challenge on Single
Objective Numerical Optimization
I CEC 2020, CEC 2021, ...: see IEEE Task Force on Benchmarking listings
(incl. BOCIA, TEVC, MDPI SIs etc.)
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 30/ 40
Abstract NLP UGPP CI References
Some More Benchmark Function Sets
The Genetic and Evolutionary Computation Conference (GECCO):
I GECCO 2014 Windfarm Layout Optimization Competition
I GECCO 2014 Permutation-based Combinatorial Optimization Problems
I GECCO 2015 Black Box Optimization (BBComp)
I GECCO 2015 Combinatorial Black-Box Optimization (CBBOC)
I GECCO 2019 Workshop  Competition on Numerical Optimization
I Swarm and Evolutionary Computation: Novel benchmark functions for
continuous multimodal optimization with comparative results (2015)
I Benchmarks for natural architecture design:
Spatial Tree Morphology Reconstruction
(seeded/pre-processed/vectorized/multi-objective)
I We prepare benchmarks for ocean exploration with underwater robots:
Underwater Glider Path Planning
(unconstraint/constraint/variable/multi-objective)
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 31/ 40
Abstract NLP UGPP CI References
Real World Industry Challenges: Motivation
I Optimization of Real World Industry Challenges (RWIC),
I selected as CEC 2011 Real World Optimization Problems,
I a benchmark set contains functions modelling the problems,
I assessment on all 22 functions of CEC 2011 set,
I functions with constraints are handled with additional care.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 32/ 40
Abstract NLP UGPP CI References
Selected Challenges in the CEC 2011 Benchmark (1/2)
I Decomposition of radio FM signals,
I determination of ternary protein structure
I Lennard-Jones inter-atom energy potential,
I parameterization of a chemical process,
I methylcyclopentane → benzene,
I control parameterization for chemical reaction in a continuous
stirred tank reactor,
I inter-atom potential in covalent Silicon systems
I Tersoff energy potential,
I radar spectrum signal broadcast parameterization,
I spread spectrum radar polly phase code design,
I electrical transmission network expansion planning,
I new lines for transmission selection.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 33/ 40
Abstract NLP UGPP CI References
Selected Challenges in the CEC 2011 Benchmark (2/2)
I Large scale transmission pricing,
I circular antenna array design,
I dynamic economic dispatch (with power generator control),
I static economic load dispatch (of power generated),
I hydrothermal scheduling (among hydro/thermal units),
I spacecraft trajectory optimization,
I Mercury (Messenger),
I Saturn (Cassini).
I The collection includes 22 functions, with constraints as:
1. non-feasible evaluation is NaN when constraints are not met, or
2. the constraints are included in the function evaluation value.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 34/ 40
Abstract NLP UGPP CI References
Conclusion: Summary  Teaching towards HPC
Summary: presented 3 HPC domains (NLP, UGPP, CI).
More: at University of Maribor, Bologna study courses for learning
(teaching, training) of Computer Science at cycles — click URL:
I level 1 (BSc)
I year 1: Programming I – e.g. C++ syntax
I year 2: Computer Architectures – e.g. assembly, microcode, ILP
I year 3: Parallell and Distributed Computing – e.g. OpenMP, MPI, CUDA
I level 2 (MSc)
I year 1: Cloud Computing Deployment and Management – e.g. arc, slurm,
containers (docker, singularity, kubernetes)
I level 3 (PhD)
I EU and other national projects research:
HPC RIVR, EuroCC, DAPHNE, ... – e.g. scaling new systems
of CI  Operational Research of ... over HPC
I IEEE Computational Intelligence Task Force on Benchmarking
I Scientific Journals (e.g. SWEVO, TEVC, JoCS, ASOC, INS)
These contribute towards Sustainable Development of HPC.
Thanks!
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 35/ 40
Abstract NLP UGPP CI References
Biography and References: Organizations
I Associate Professorat University of Maribor, Slovenia
I Continuous research programme funded by Slovenian Research Agency,
P2-0041: Computer Systems, Methodologies, and Intelligent Services
I Associate Editor: Swarm and Evolutionary Computation (SWEVO)
I IEEE (Institute of Electrical and Electronics Engineers) senior
I IEEE Computational Intelligence Society (CIS), senior member
I IEEE CIS Task Force on Benchmarking, chair
I IEEE CIS, Slovenia Section Chapter (CH08873), chair
I IEEE Slovenia Section, vice chair
I IEEE Young Professionals Slovenia, past chair
I ACM SIGEVO (Special Interest Group on Genetic and Evolutionary Computation); EurAI; SLAIS
I Co-operation in Science and Techology (COST) Association
Management Committee, member:
I CA COST Action CA15140: Improving Applicability of Nature-Inspired
Optimisation by Joining Theory and Practice (ImAppNIO), WG3 VC
I ICT COST Action IC1406 High-Performance Modelling and Simulation
for Big Data Applications (cHiPSet); SI-HPC; HPC-RIVR user
I EU H2020 Research and Innovation project, holder for UM part: Integrated
Data Analysis Pipelines for Large-Scale Data Management, HPC, and Machine
Learning (DAPHNE), https://cordis.europa.eu/project/id/957407
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 36/ 40
Abstract NLP UGPP CI References
Biography and References: Top Publications
I Aleš Zamuda, Elena Lloret. Optimizing Data-Driven Models for Summarization as Parallel Tasks.
Journal of Computational Science, 2020, vol. 42, pp. 101101. DOI 10.1016/j.jocs.2020.101101.
I A. Zamuda, J. D. Hernández Sosa. Success history applied to expert system for underwater glider path
planning using differential evolution. Expert Systems with Applications, 2019, vol. 119, pp. 155-170.
DOI 10.1016/j.eswa.2018.10.048
I A. Viktorin, R. Senkerik, M. Pluhacek, T. Kadavy, A. Zamuda. Distance Based Parameter Adaptation
for Success-History based Differential Evolution. Swarm and Evolutionary Computation, 2019, vol. 50,
pp. 100462. DOI 10.1016/j.swevo.2018.10.013.
I A. Zamuda, J. Brest. Self-adaptive control parameters’ randomization frequency and propagations in
differential evolution. Swarm and Evolutionary Computation, 2015, vol. 25C, pp. 72-99.
DOI 10.1016/j.swevo.2015.10.007.
I A. Zamuda, J. D. Hernández Sosa, L. Adler. Constrained Differential Evolution Optimization for
Underwater Glider Path Planning in Sub-mesoscale Eddy Sampling. Applied Soft Computing, 2016,
vol. 42, pp. 93-118. DOI 10.1016/j.asoc.2016.01.038.
I A. Zamuda, J. D. Hernández Sosa. Differential Evolution and Underwater Glider Path Planning
Applied to the Short-Term Opportunistic Sampling of Dynamic Mesoscale Ocean Structures.
Applied Soft Computing, vol. 24, November 2014, pp. 95-108. DOI 10.1016/j.asoc.2014.06.048.
I A. Zamuda, J. Brest. Vectorized Procedural Models for Animated Trees Reconstruction using
Differential Evolution. Information Sciences, vol. 278, pp. 1-21, 2014. DOI 10.1016/j.ins.2014.04.037.
I A. Zamuda, J. Brest. Environmental Framework to Visualize Emergent Artificial Forest Ecosystems.
Information Sciences, vol. 220, pp. 522-540, 2013. DOI 10.1016/j.ins.2012.07.031.
I A. Glotić, A. Zamuda. Short-term combined economic and emission hydrothermal optimization by
surrogate differential evolution. Applied Energy, 1 March 2015, vol. 141, pp. 42-56.
DOI 10.1016/j.apenergy.2014.12.020.
I H. Hamann, Y. Khaluf, J. Botev, M. Divband Soorati, E. Ferrante, O. Kosak, J.-M. Montanier, S.
Mostaghim, R. Redpath, J. Timmis, F. Veenstra, M. Wahby and A. Zamuda. Hybrid Societies:
Challenges and Perspectives in the Design of Collective Behavior in Self-organizing Systems.
Frontiers in Robotics and AI, 2016, vol. 3, no. 14. DOI 10.3389/frobt.2016.00014.
I J. Šilc, A. Zamuda. Special Issue on ”Bioinspired Optimization” (guest editors). Informatica - An
International Journal of Computing and Informatics, 2015, vol. 39, no. 2, pp. 1-122.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 37/ 40
Abstract NLP UGPP CI References
Biography and References: Bound Specific to HPC
PROJECTS:
I DAPHNE: Integrated Data Analysis Pipelines for Large-Scale Data
Management, HPC, and Machine Learning
I ICT COST Action IC1406 High-Performance Modelling and Simulation for Big
Data Applications
I SLING: Slovenian national supercomputing network
I SI-HPC: Slovenian corsortium for High-Performance Computing
I UM HPC-RIVR: Supercomputer at UM, https://www.hpc-rivr.si/
I SmartVillages: Smart digital transformation of villages in the Alpine Space
I Interreg Alpine Space,
https://www.alpine-space.eu/projects/smartvillages/en/home
I Interactive multimedia digital signage (PKP, Adin DS)
EDITOR:
I SWEVO (Top Journal), Associate Editor
I Mathematics-MDPI, Special Issue: Evolutionary Algorithms in Engineering Design Optimization
I Journal of advanced engineering and computation (member of editorial board since 2019). Viet Nam: Ton
Duc Thang University, 2017-. ISSN 2588-123X.
I Cloud Computing and Data Science (Associate Editor, since 2019). Universal Wiser Publisher Pte.Ltd.
I D. Gleich, P. Planinšič, A. Zamuda. 2018 25th International Conference on Systems, Signals and Image
Processing (IWSSIP). IEEE Xplore, Maribor, 20-22 June 2018.
I General Chair: 7-th Joint International Conferences on Swarm, Evolutionary and Memetic Computing
Conference (SEMCCO 2019)  Fuzzy And Neural Computing Conference (FANCCO 2019), Maribor,
Slovenia, EU, 10-12 July 2019; co-editors: Aleš Zamuda, Swagatam Das, Ponnuthurai Nagaratnam
Suganthan, Bijaya Ketan Panigrahi.
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 38/ 40
Abstract NLP UGPP CI References
Biography and References: More on HPC
RESEARCH PUBLICATIONS:
I Aleš Zamuda, Elena Lloret. Optimizing Data-Driven Models for Summarization as Parallel Tasks.
Journal of Computational Science, 2020, vol. 42, pp. 101101. DOI 10.1016/j.jocs.2020.101101.
I Aleš Zamuda, Vincenzo Crescimanna, Juan C. Burguillo, Joana Matos Dias, Katarzyna Wegrzyn-Wolska,
Imen Rached, Horacio González-Vélez, Roman Senkerik, Claudia Pop, Tudor Cioara, Ioan Salomie, Andrea
Bracciali. Forecasting Cryptocurrency Value by Sentiment Analysis: An HPC-Oriented Survey of the
State-of-the-Art in the Cloud Era. Kolodziej J., González-Vélez H. (eds) High-Performance Modelling and
Simulation for Big Data Applications. Lecture Notes in Computer Science, vol 11400, 2019, pp. 325-349.
DOI 10.1007/978-3-030-16272-6 12.
I Nenad Karolija, Aleš Zamuda. On cloud-supported web-based integrated development environment for
programming dataflow architectures. MILUTINOVIĆ, Veljko (ur.), KOTLAR, Milos (ur.). Exploring the
DataFlow supercomputing paradigm: example algorithms for selected applications, (Computer
communications and networks (Internet), ISSN 2197-8433), 2019, pp. 41-51. DOI
10.1007/978-3-030-13803-5 2.
I Simone Spolaor, Marco Gribaudo, Mauro Iacono, Tomas Kadavy, Zuzana Komı́nková Oplatková, Giancarlo
Mauri, Sabri Pllana, Roman Senkerik, Natalija Stojanovic, Esko Turunen, Adam Viktorin, Salvatore
Vitabile, Aleš Zamuda, Marco S. Nobile. Towards Human Cell Simulation. Kolodziej J., González-Vélez H.
(eds) High-Performance Modelling and Simulation for Big Data Applications. Lecture Notes in
Computer Science, vol 11400, 2019, pp. 221-249. DOI 10.1007/978-3-030-16272-6 8.
I A. Zamuda, J. D. Hernandez Sosa, L. Adler. Improving Constrained Glider Trajectories for Ocean Eddy
Border Sampling within Extended Mission Planning Time. IEEE Congress on Evolutionary Computation
(CEC) 2016, 2016, pp. 1727-1734.
I A. Zamuda. Function evaluations upto 1e+12 and large population sizes assessed in distance-based
success history differential evolution for 100-digit challenge and numerical optimization scenarios
(DISHchain 1e+12): a competition entry for ”100-digit challenge, and four other numerical optimization
competitions” at the genetic and evolutionary computation conference (GECCO) 2019. Proceedings of the
Genetic and Evolutionary Computation Conference Companion (GECCO 2019), 2019, pp. 11-12.
I ... several more experiments for papers run using HPCs.
I ... also, pedagogic materials in Slovenian and English — see Conclusion .
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 39/ 40
Abstract NLP UGPP CI References
Promo materials: Calls for Papers, Informational Websites
CS FERI WWW
CIS TFoB
CFPs WWW
LinkedIn
Twitter
Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP  CI 40/ 40

Mais conteúdo relacionado

Semelhante a Parallelization of Benchmarking using HPC: Text Summarization in Natural Language Processing (NLP), Glider Piloting in Deep-sea Missions, and Search Algorithms in Computational Intelligence (CI)

An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...
An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...
An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...IRJET Journal
 
ACLP Flexible Solutions To Complex Problems
ACLP  Flexible Solutions To Complex ProblemsACLP  Flexible Solutions To Complex Problems
ACLP Flexible Solutions To Complex ProblemsAmy Isleb
 
Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...
Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...
Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...Daniel Valcarce
 
DMDW Lesson 08 - Further Data Mining Algorithms
DMDW Lesson 08 - Further Data Mining AlgorithmsDMDW Lesson 08 - Further Data Mining Algorithms
DMDW Lesson 08 - Further Data Mining AlgorithmsJohannes Hoppe
 
Semantics and optimisation of the SPARQL1.1 federation extension
Semantics and optimisation of the SPARQL1.1 federation extensionSemantics and optimisation of the SPARQL1.1 federation extension
Semantics and optimisation of the SPARQL1.1 federation extensionOscar Corcho
 
A scalable collaborative filtering framework based on co clustering
A scalable collaborative filtering framework based on co clusteringA scalable collaborative filtering framework based on co clustering
A scalable collaborative filtering framework based on co clusteringAllenWu
 
Rapport_Cemracs2012
Rapport_Cemracs2012Rapport_Cemracs2012
Rapport_Cemracs2012Jussara F.M.
 
Neural Style Transfer in Practice
Neural Style Transfer in PracticeNeural Style Transfer in Practice
Neural Style Transfer in PracticeKhalilBergaoui
 
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTION
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTIONA COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTION
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTIONIJCSEA Journal
 
cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...
cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...
cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...Lifeng (Aaron) Han
 
A minimization approach for two level logic synthesis using constrained depth...
A minimization approach for two level logic synthesis using constrained depth...A minimization approach for two level logic synthesis using constrained depth...
A minimization approach for two level logic synthesis using constrained depth...IAEME Publication
 
IRJET- K-SVD: Dictionary Developing Algorithms for Sparse Representation ...
IRJET-  	  K-SVD: Dictionary Developing Algorithms for Sparse Representation ...IRJET-  	  K-SVD: Dictionary Developing Algorithms for Sparse Representation ...
IRJET- K-SVD: Dictionary Developing Algorithms for Sparse Representation ...IRJET Journal
 
Duality Theory in Multi Objective Linear Programming Problems
Duality Theory in Multi Objective Linear Programming ProblemsDuality Theory in Multi Objective Linear Programming Problems
Duality Theory in Multi Objective Linear Programming Problemstheijes
 
A0311010106
A0311010106A0311010106
A0311010106theijes
 

Semelhante a Parallelization of Benchmarking using HPC: Text Summarization in Natural Language Processing (NLP), Glider Piloting in Deep-sea Missions, and Search Algorithms in Computational Intelligence (CI) (20)

An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...
An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...
An Optimized Parallel Algorithm for Longest Common Subsequence Using Openmp –...
 
ACLP Flexible Solutions To Complex Problems
ACLP  Flexible Solutions To Complex ProblemsACLP  Flexible Solutions To Complex Problems
ACLP Flexible Solutions To Complex Problems
 
Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...
Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...
Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recom...
 
DMDW Lesson 08 - Further Data Mining Algorithms
DMDW Lesson 08 - Further Data Mining AlgorithmsDMDW Lesson 08 - Further Data Mining Algorithms
DMDW Lesson 08 - Further Data Mining Algorithms
 
Semantics and optimisation of the SPARQL1.1 federation extension
Semantics and optimisation of the SPARQL1.1 federation extensionSemantics and optimisation of the SPARQL1.1 federation extension
Semantics and optimisation of the SPARQL1.1 federation extension
 
A scalable collaborative filtering framework based on co clustering
A scalable collaborative filtering framework based on co clusteringA scalable collaborative filtering framework based on co clustering
A scalable collaborative filtering framework based on co clustering
 
Rapport_Cemracs2012
Rapport_Cemracs2012Rapport_Cemracs2012
Rapport_Cemracs2012
 
Neural Style Transfer in Practice
Neural Style Transfer in PracticeNeural Style Transfer in Practice
Neural Style Transfer in Practice
 
Neural Style Transfer in practice
Neural Style Transfer in practiceNeural Style Transfer in practice
Neural Style Transfer in practice
 
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTION
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTIONA COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTION
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTION
 
cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...
cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...
cushLEPOR uses LABSE distilled knowledge to improve correlation with human tr...
 
A minimization approach for two level logic synthesis using constrained depth...
A minimization approach for two level logic synthesis using constrained depth...A minimization approach for two level logic synthesis using constrained depth...
A minimization approach for two level logic synthesis using constrained depth...
 
IRJET- K-SVD: Dictionary Developing Algorithms for Sparse Representation ...
IRJET-  	  K-SVD: Dictionary Developing Algorithms for Sparse Representation ...IRJET-  	  K-SVD: Dictionary Developing Algorithms for Sparse Representation ...
IRJET- K-SVD: Dictionary Developing Algorithms for Sparse Representation ...
 
Efficient projections
Efficient projectionsEfficient projections
Efficient projections
 
Efficient projections
Efficient projectionsEfficient projections
Efficient projections
 
SYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMING
SYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMINGSYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMING
SYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMING
 
SYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMING
SYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMINGSYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMING
SYNTAX AND SEMANTICS FOR CINNAMON PROGRAMMING
 
Duality Theory in Multi Objective Linear Programming Problems
Duality Theory in Multi Objective Linear Programming ProblemsDuality Theory in Multi Objective Linear Programming Problems
Duality Theory in Multi Objective Linear Programming Problems
 
A0311010106
A0311010106A0311010106
A0311010106
 
AI applications in education, Pascal Zoleko, Flexudy
AI applications in education, Pascal Zoleko, FlexudyAI applications in education, Pascal Zoleko, Flexudy
AI applications in education, Pascal Zoleko, Flexudy
 

Mais de University of Maribor

Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...
Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...
Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...University of Maribor
 
Deployment of Randomised Optimisation Algorithms Benchmarking in DAPHNE
Deployment of Randomised Optimisation Algorithms Benchmarking in DAPHNEDeployment of Randomised Optimisation Algorithms Benchmarking in DAPHNE
Deployment of Randomised Optimisation Algorithms Benchmarking in DAPHNEUniversity of Maribor
 
Evolutionary Optimization Algorithms & Large-Scale Machine Learning
Evolutionary Optimization Algorithms & Large-Scale Machine LearningEvolutionary Optimization Algorithms & Large-Scale Machine Learning
Evolutionary Optimization Algorithms & Large-Scale Machine LearningUniversity of Maribor
 
Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...
Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...
Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...University of Maribor
 
EuroHPC AI in DAPHNE and Text Summarization
EuroHPC AI in DAPHNE and Text SummarizationEuroHPC AI in DAPHNE and Text Summarization
EuroHPC AI in DAPHNE and Text SummarizationUniversity of Maribor
 
Load balancing energy power plants with high-performance data analytics (HPDA...
Load balancing energy power plants with high-performance data analytics (HPDA...Load balancing energy power plants with high-performance data analytics (HPDA...
Load balancing energy power plants with high-performance data analytics (HPDA...University of Maribor
 
ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...
ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...
ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...University of Maribor
 
Poročilo ODBORA CIS (CH08873) za leto 2020
Poročilo ODBORA CIS (CH08873) za leto 2020Poročilo ODBORA CIS (CH08873) za leto 2020
Poročilo ODBORA CIS (CH08873) za leto 2020University of Maribor
 
Poročilo ODBORA CIS (CH08873) za leto 2019
Poročilo ODBORA CIS (CH08873) za leto 2019 Poročilo ODBORA CIS (CH08873) za leto 2019
Poročilo ODBORA CIS (CH08873) za leto 2019 University of Maribor
 
Poročilo ODBORA CIS (CH08873) za leto 2022
Poročilo ODBORA CIS (CH08873) za leto 2022Poročilo ODBORA CIS (CH08873) za leto 2022
Poročilo ODBORA CIS (CH08873) za leto 2022University of Maribor
 
HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...
HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...
HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...University of Maribor
 
Delo vodje odbora IEEE: naloge, dobre prakse, poročanje
Delo vodje odbora IEEE: naloge, dobre prakse, poročanjeDelo vodje odbora IEEE: naloge, dobre prakse, poročanje
Delo vodje odbora IEEE: naloge, dobre prakse, poročanjeUniversity of Maribor
 
Speeding Up Vectorized Benchmarking of Optimization Algorithms
Speeding Up Vectorized Benchmarking of Optimization AlgorithmsSpeeding Up Vectorized Benchmarking of Optimization Algorithms
Speeding Up Vectorized Benchmarking of Optimization AlgorithmsUniversity of Maribor
 
IEEE Slovenia: Introduction (in Slovene), with details in English
IEEE Slovenia: Introduction (in Slovene), with details in EnglishIEEE Slovenia: Introduction (in Slovene), with details in English
IEEE Slovenia: Introduction (in Slovene), with details in EnglishUniversity of Maribor
 
IEEE Slovenia CIS in 2021 (a report in Slovene language)
IEEE Slovenia CIS in 2021 (a report in Slovene language)IEEE Slovenia CIS in 2021 (a report in Slovene language)
IEEE Slovenia CIS in 2021 (a report in Slovene language)University of Maribor
 
Adaptive Constraint Handling and Success History Differential Evolution for C...
Adaptive Constraint Handling and Success History Differential Evolution for C...Adaptive Constraint Handling and Success History Differential Evolution for C...
Adaptive Constraint Handling and Success History Differential Evolution for C...University of Maribor
 

Mais de University of Maribor (17)

Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...
Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...
Poročilo odbora CIS (CH08873) za leto 2023 na letni skupščini IEEE Slovenija ...
 
Deployment of Randomised Optimisation Algorithms Benchmarking in DAPHNE
Deployment of Randomised Optimisation Algorithms Benchmarking in DAPHNEDeployment of Randomised Optimisation Algorithms Benchmarking in DAPHNE
Deployment of Randomised Optimisation Algorithms Benchmarking in DAPHNE
 
Evolutionary Optimization Algorithms & Large-Scale Machine Learning
Evolutionary Optimization Algorithms & Large-Scale Machine LearningEvolutionary Optimization Algorithms & Large-Scale Machine Learning
Evolutionary Optimization Algorithms & Large-Scale Machine Learning
 
Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...
Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...
Solving 100-Digit Challenge with Score 100 by Extended Running Time and Paral...
 
EuroHPC AI in DAPHNE and Text Summarization
EuroHPC AI in DAPHNE and Text SummarizationEuroHPC AI in DAPHNE and Text Summarization
EuroHPC AI in DAPHNE and Text Summarization
 
EuroHPC AI in DAPHNE
EuroHPC AI in DAPHNEEuroHPC AI in DAPHNE
EuroHPC AI in DAPHNE
 
Load balancing energy power plants with high-performance data analytics (HPDA...
Load balancing energy power plants with high-performance data analytics (HPDA...Load balancing energy power plants with high-performance data analytics (HPDA...
Load balancing energy power plants with high-performance data analytics (HPDA...
 
ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...
ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...
ULPGC2023-Erasmus+lectures_Ales_Zamuda_SystemsTheory+IntelligentAutonomousSys...
 
Poročilo ODBORA CIS (CH08873) za leto 2020
Poročilo ODBORA CIS (CH08873) za leto 2020Poročilo ODBORA CIS (CH08873) za leto 2020
Poročilo ODBORA CIS (CH08873) za leto 2020
 
Poročilo ODBORA CIS (CH08873) za leto 2019
Poročilo ODBORA CIS (CH08873) za leto 2019 Poročilo ODBORA CIS (CH08873) za leto 2019
Poročilo ODBORA CIS (CH08873) za leto 2019
 
Poročilo ODBORA CIS (CH08873) za leto 2022
Poročilo ODBORA CIS (CH08873) za leto 2022Poročilo ODBORA CIS (CH08873) za leto 2022
Poročilo ODBORA CIS (CH08873) za leto 2022
 
HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...
HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...
HPC Deployment / Use Cases (EVEREST + DAPHNE: Workshop on Design and Programm...
 
Delo vodje odbora IEEE: naloge, dobre prakse, poročanje
Delo vodje odbora IEEE: naloge, dobre prakse, poročanjeDelo vodje odbora IEEE: naloge, dobre prakse, poročanje
Delo vodje odbora IEEE: naloge, dobre prakse, poročanje
 
Speeding Up Vectorized Benchmarking of Optimization Algorithms
Speeding Up Vectorized Benchmarking of Optimization AlgorithmsSpeeding Up Vectorized Benchmarking of Optimization Algorithms
Speeding Up Vectorized Benchmarking of Optimization Algorithms
 
IEEE Slovenia: Introduction (in Slovene), with details in English
IEEE Slovenia: Introduction (in Slovene), with details in EnglishIEEE Slovenia: Introduction (in Slovene), with details in English
IEEE Slovenia: Introduction (in Slovene), with details in English
 
IEEE Slovenia CIS in 2021 (a report in Slovene language)
IEEE Slovenia CIS in 2021 (a report in Slovene language)IEEE Slovenia CIS in 2021 (a report in Slovene language)
IEEE Slovenia CIS in 2021 (a report in Slovene language)
 
Adaptive Constraint Handling and Success History Differential Evolution for C...
Adaptive Constraint Handling and Success History Differential Evolution for C...Adaptive Constraint Handling and Success History Differential Evolution for C...
Adaptive Constraint Handling and Success History Differential Evolution for C...
 

Último

Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsSumit Kumar yadav
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINsankalpkumarsahoo174
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoSérgio Sacani
 
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...Sérgio Sacani
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptxRajatChauhan518211
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bSérgio Sacani
 
VIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C PVIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C PPRINCE C P
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfSumit Kumar yadav
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡anilsa9823
 
Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPirithiRaju
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)Areesha Ahmad
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSSLeenakshiTyagi
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencySheetal Arora
 

Último (20)

Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questions
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on Io
 
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptx
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
VIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C PVIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C P
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdf
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
 
Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdf
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSS
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 

Parallelization of Benchmarking using HPC: Text Summarization in Natural Language Processing (NLP), Glider Piloting in Deep-sea Missions, and Search Algorithms in Computational Intelligence (CI)

  • 1. Abstract NLP UGPP CI References Parallelization of Benchmarking using HPC: Text Summarization in Natural Language Processing (NLP), Glider Piloting in Deep-sea Missions, and Search Algorithms in Computational Intelligence (CI) ASHPC21, Austrian-Slovenian High-Performance Computing Meeting Institute of Information Science in Maribor, Slovenia 1 May – 2 June, 2021 (online exclusively via livestream) Aleš Zamuda ales.zamuda@um.si Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 1/ 40
  • 2. Abstract NLP UGPP CI References Introduction: Overview This contribution focuses on I recent developments and trends I in terms of efficient and successful I high-performance computing (HPC) applications. Real examples: science and HPC Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 2/ 40
  • 3. Abstract NLP UGPP CI References Introduction: Aims of this Talk at ASHPC21 Meeting I First (5 minutes), a collaboration benefiting from HPC: a state-of-the-art topic of text summarization for NLP (part of ”Big Data”), I spanning over the time curse of successful HPC initiatives including Slovenia: SLING → SIHPC → ImAppNIO → cHiPSet → HPC RIVR → TFoB → EuroCC → DAPHNE I Second (+10 minutes), additional success stories are listed, like those developed through program funded unit P2-0041, HPC RIVR project, and projects by EU under programs like Erasmus+, COST (Cooperation in Science and Technology) and H2020 (Horizon 2020). I Third (5 minutes), this contribution aims at leveraging potential opportunities in NLP and HPC for shared and collaborative synergies, enhancing sustainable HPC development. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 3/ 40
  • 4. Abstract NLP UGPP CI References HPC Application 1: Text Summarization I NLP and computational linguistics for Text Summarization: I Multi-Document Text Summarization is a hard CI challenge. I Basically, an evolutionary algorithm is applied for summarization, I it is a state-of-the-art topic of text summarization for NLP (part of ”Big Data”) and presented as a collaboration [JoCS2020], acknowledging several efforts. I we add: self-adaptation of optimization control parameters; analysis through benchmarking using HPC, and apply additional NLP tools. I How it works: for the abstract, sentences from original text are selected for full inclusion (extraction). I To extract a combination of sentences: I can be computationally demanding, I we use heuristic optimization, I the time to run optimization can be limited. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 4/ 40
  • 5. Abstract NLP UGPP CI References 1 – Preprocessing (environment sensing, knowledge representation) (1/2) 1) The files of documents are each taken through the following process using NLP (Natural Language Processing) tools: INPUT CORPUS NATURAL LANGUAGE PROCESSING ANALYSIS CONCEPTS DISTRIBUTION PER SENTENCES MATRIX OF CONCEPTS PROCESSING CORPUS PREPROCESSING PHASE OPTIMIZATION TASKS EXECUTION PHASE ASSEMBLE TASK DESCRIPTION SUBMIT TASKS TO PARALLEL EXECUTION OPTIMIZER + TASK DATA ROUGE EVALUATION 2) For each document is D, sentences are indexed using NLP tools. I Terms across sentences are determined using a semantic analysis using both: I coreference resolution (using WordNet) and I a Concept Matrix (from Freeling). Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 5/ 40
  • 6. Abstract NLP UGPP CI References 1 – Preprocessing (environment sensing, knowledge representation) (2/2) I 3) For each i-th term (wi ), during indexing I number of occurences in the text is gathered, and I number of occurences (nk ) of a term in some k-th statement, I 4) For each term wi in the document, inverse frequency: isfw i = log( n nk ), I where n denotes number of statements in the document, and I nk number of statements including a term wi . I 5) To conclude preprocessing, for each term in the document, a weight is calculated: wi,k = tfi,kisfk, where tfik is number of occurences (term frequency) of a term wk in a statement si . Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP & CI 6/ 40
  • 7. Abstract NLP UGPP CI References 2 – Summary Optimization (1/3) I Sentence combination (X) is optimized using jDE algorithm: I as a 0/1 knapsack problem, we want to include optimal selection of statements in the final output I an i-th sentence si is selected (xi = 1) or unselected (xi = 0). I a) Price of a knapsack (its fitness) should be maximized, I the fitness represents a ratio between content coverage, V (X), and redundancy, R(X): f (X) = V (X) R(X) , I considering a constraint: the summary length is L ± words. I Constraint handling with solutions: I each feasable solution is better than unfeasable, I unfeasable compared by constraint value (lower better), I feasable compared by fitness (higher better). Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 7/ 40
  • 8. Abstract NLP UGPP CI References 2 – Summary Optimization (2/3) I b) Content coverage V (X) is computed as a double sum of similarities (defined at d)): V (X) = n−1 X i=1 n X j=i+1 (sim(si , O) + sim(sj , O))xi,j , I where xi,j denotes inclusion of both statement, si , and sj , I xi,j is only 1 if xi = xj = 1, otherwise 0, I and O is a vector of average term weights wi,k : O = (o1, o2, ..., om) for all i = {1..m} different text terms: oi = Pn j=1 wi,j n . I c) Redundance R(X) is also measured as double similarity (defined at d)) sum for all statements: R(X) = n−1 X i=1 n X j=i+1 sim(si , sj )xi,j , I where xi,j denotes inclusion of both statement, si , and sj , I again, xi,j is only 1 if xi = xj = 1, otherwise 0. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 8/ 40
  • 9. Abstract NLP UGPP CI References 2 – Summary Optimization (3/3) I d) Similarity between statements si = [wi,1, wi,2, ..., wi,m] and sj = [wj,1, wj,2, ..., wj,m] is computed: sim(si , sj ) = m X k=1 wi,kwj,k pPm k=1 wi,kwi,k Pm k=1 wj,kwj,k , where wi,k is term weight (defined in 5)) and m number of all terms in text. I e) When concluded: I the selected statements from the best assessed combination are printed, I in order as they appear in the text, and I the summary is stored. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 9/ 40
  • 10. Abstract NLP UGPP CI References Summary Optimization — Algorithm Pseudocode The detailed new method called CaBiSDETS is developed in the HPC approach comprising of: I a version of evolutionary algorithm (Differential Evolution, DE), I self-adaptation, binarization, constraint adjusting, and some more pre-computation, I optimizing the inputs to define the summarization optimization model. Aleš Zamuda, Elena Lloret. Optimizing Data-Driven Models for Summarization as Parallel Tasks. Journal of Computational Science, 2020, vol. 42, pp. 101101. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 10/ 40
  • 11. Abstract NLP UGPP CI References Running the Tasks on HPC: ARC Job Preparation Submission, Results Retrieval Merging [JoCS2020] Through an HPC approach and by parallelization of tasks, a data-driven summarization model optimization yields improved benchmark metric results (drawn using gnuplot merge). Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 11/ 40
  • 12. Abstract NLP UGPP CI References Results Published in Journal of Computational Science The most interesting finding of the HPC study though is that I the fitness of the NLP model keeps increasing with prolonging the dedicated HPC resources (see below) and that I the fitness improvement correlates with ROUGE evaluation in the benchmark, i.e. better summaries. -0.05 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 1 10 100 1000 10000 ROUGE-1R ROUGE-2R ROUGE-LR ROUGE-SU4R Fitness (scaled) Hence, the use of HPC significantly contributes to capability of this NLP challenge. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 12/ 40
  • 13. Abstract NLP UGPP CI References HPC Application 2: Underwater Glider: Autonomous, Unmanned, Robotic I underwater glider – navigating sea oceans, I Autonomous Underwater Vehicle (AUV) 6= Unmanned Aerial Vehicle (UAV) I AUV Slocum model (expertise in domain of ULPGC, work with J. D. Hernández Sosa) Images: ”Photo: Richard Watt/MOD” (License: OGL v1.0) Slocum-Glider-Auvpicture 5.jpg (License: Public Domain) MiniU.jpg (License: CC-BY-SA 3.0) Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 13/ 40
  • 14. Abstract NLP UGPP CI References The Buoyancy Drive and Submarine Probes Usefulness I Driving ”yoyo” uses little energy, most only on descent and rise (pump); also for maintaining direction little power is consumed. + Use: improving ocean models with real data, + the real data at the point of capture, + sampling flow of oil discharges, + monitoring cable lines, and + real-time monitoring of different sensor data. 1 http://spectrum.ieee.org/image/1523708 Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 14/ 40
  • 15. Abstract NLP UGPP CI References Preparations – Simulation Scenarios https://www.google.si/maps/@28.059806,-15.998355,650054m/data=!3m1!1e3 Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 15/ 40
  • 16. Abstract NLP UGPP CI References Trajectory Optimization: P201,ESTOC2013 3 + BigData, MyOcean IBI, satelite link, GPS location The real trajectory and collected data is available in a Google Earth KML file at the EGO network: http://www.ego-network.org/dokuwiki/doku.php?glider=P201,ESTOC2013_3 Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 16/ 40
  • 17. Abstract NLP UGPP CI References Constrained Differential Evolution Optimization for Underwater Glider Path Planning in Sub-mesoscale Eddy Sampling I Corridor-constrained optimization: eddy border region sampling I new challenge for UGPP DE I Feasible path area is constrained I trajectory in corridor around the border of an ocean eddy The objective of the glider here is to sample the oceanographic variables more efficiently, while keeping a bounded trajectory Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 17/ 40
  • 18. Abstract NLP UGPP CI References Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 18/ 40
  • 19. Abstract NLP UGPP CI References Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 19/ 40
  • 20. Abstract NLP UGPP CI References Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 20/ 40
  • 21. Abstract NLP UGPP CI References Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 21/ 40
  • 22. Abstract NLP UGPP CI References HoP — New Trajectories: Success history applied to expert system for underwater glider path planning using differential evolution I Improved underwater glider path planning mission scenarios: optimization with L-SHADE. I Several configured algorithms are also compared to, analysed, and further improved. I Outranked all other previous results from literature and ranked first in comparison. I New algorithm yielded practically stable and competitive output trajectories. I UGPP unconstrained scenarios — contributed significantly to the capacity of the decision-makers for mission plannings. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 22/ 40
  • 23. Abstract NLP UGPP CI References Ranking UGPP — Benchmarking Aggregation I Statistically, all results from previous paper were outperformed. I Main reasons: tuning (NP), parameter control (L-SHADE). Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 23/ 40
  • 24. Abstract NLP UGPP CI References HPC Application 3: Multi-application domain generalized Computational Intelligence (CI) through HPC I With the ubiquity of HPC and Cloud Computing, I connectible using versatile interfaces for their utilisation, I example successes of these systems is computational intelligence. I One of designs for these services is: I using evolutionary optimization approaches, I needing much efficiently parallelizable data processing power. I There are several application domains of this approach: I generalized numerical functions problems and I other parallel real world problems, such as I text processing, I molecular modelling, I evolutionary computer vision, and I robotics. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 24/ 40
  • 25. Abstract NLP UGPP CI References CI Algorithm Design: Control Parameters Self-Adaptation I Through more suitable values of control parameters the search process exhibits a better convergence (CI — Computational Intelligence), I therefore the search converges faster to better solutions, which survive with greater probability and they create more offspring and propagate their control parameters I Recent study with cca. 10 million runs of SPSRDEMMS: A. Zamuda, J. Brest. Self-adaptive control parameters’ randomization frequency and propagations in differential evolution. Swarm and Evolutionary Computation, 2015, vol. 25C, pp. 72-99. DOI 10.1016/j.swevo.2015.10.007. – SWEVO 2015 RAMONA / SNIP 5.220 I Deployed using arcsub. I Update: DISH algorithm — https://doi.org/10.1016/j.swevo.2018.10.013 (Outperforms on CEC 2017 functions.) Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 25/ 40
  • 26. Abstract NLP UGPP CI References Existing Challenges: Benchmarks for Known Environments Inspired by previous computational optimization competitions in continuous settings that used test functions for optimization application domains: I single-objective: CEC 2005, 2013, 2014, 2015 I constrained: CEC 2006, CEC 2007, CEC 2010 I multi-modal: CEC 2010, SWEVO 2016 I black-box (target value): BBOB 2009, COCO 2016 I noisy optimization: BBOB 2009 I large-scale: CEC 2008, CEC 2010 I dynamic: CEC 2009, CEC 2014 I real-world: CEC 2011 I computationally expensive: CEC 2013, CEC 2015 I learning-based: CEC 2015 I 100-digit (50% targets): 2019 joined CEC, SEMCCO, GECCO I multi-objective: CEC 2002, CEC 2007, CEC 2009, CEC 2014 I bi-objective: CEC 2008 I many objective: CEC 2018 Tuning/ranking/hyperheuristics use. → DEs as usual winner algorithms. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 26/ 40
  • 27. Abstract NLP UGPP CI References IEEE Congress on Evolutionary Computation (CEC) Competitions (1/4) I Storn, Rainer, and Kenneth V. Price. ”Minimizing the Real Functions of the ICEC’96 Contest by Differential Evolution.” International Conference on Evolutionary Computation. 1996. I ... I CEC 2005 Special Session / Competition on Evolutionary Real Parameter single objective optimization I CEC 2006 Special Session / Competition on Evolutionary Constrained Real Parameter single objective optimization I CEC 2007 Special Session / Competition on Performance Assessment of real-parameter MOEAs I CEC 2008 Special Session / Competition on large scale single objective global optimization with bound constraints I CEC 2008 Scale-Invariant Optimisation Competition ”Mountains or Molehills” I CEC 2009 Special Session / Competition on Dynamic Optimization (Primarily composition functions were used) I CEC 2009 Special Session / Competition on Performance Assessment of real-parameter MOEAs Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 27/ 40
  • 28. Abstract NLP UGPP CI References IEEE Congress on Evolutionary Computation (CEC) Competitions (2/4) I CEC 2010 Special Session / Competition on large-scale single objective global optimization with bound constraints I CEC 2010 Special Session / Competition on Evolutionary Constrained Real Parameter single objective optimization I CEC 2010 Special Session on Niching Introduces novel scalable test problems I CEC 2011 Competition on Testing Evolutionary Algorithms on Real-world Numerical Optimization Problems I CEC 2013 Special Session / Competition on Real Parameter Single Objective Optimization I CEC 2014 Special Session / Competition on Real Parameter Single Objective Optimization (incorporates expensive functions) I CEC 2014: Dynamic MOEA Benchmark Problems Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 28/ 40
  • 29. Abstract NLP UGPP CI References IEEE Congress on Evolutionary Computation (CEC) Competitions (3/4) I CEC 2015 Special Session / Competition on Real Parameter Single Objective Optimization (incorporates 3 scenarios) I CEC 2015 Black Box Optimization Competition I CEC 2015 Dynamic Multi-Objective Optimization I CEC 2015 Optimization of Big Data I CEC 2015 Large Scale Global Optimization I CEC 2015 Bound Constrained Single-Objective Numerical Optimization I CEC 2015 Optimisation of Problems with Multiple Interdependent Components I CEC 2015 Niching Methods for Multimodal Optimization Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 29/ 40
  • 30. Abstract NLP UGPP CI References IEEE Congress on Evolutionary Computation (CEC) Competitions (4/4) I CEC 2016 Special Session / Competition on Real Parameter Single Objective Optimization (incorporates 4 scenarios) I CEC 2016 Big Optimization (BigOpt2016) I CEC 2016 Niching Methods for Multimodal Optimization I CEC 2016 Special Session Associated with Competition on Bound Constrained Single Objective Numerical Optimization I CEC2017 Special Session / Competition on Real Parameter Single Objective Optimization (also constrained) I CEC2018 Special Session / Competition on Real Parameter Single Objective Optimization I CEC2019 Special Session / Competition on 100-Digit Challenge on Single Objective Numerical Optimization I CEC 2020, CEC 2021, ...: see IEEE Task Force on Benchmarking listings (incl. BOCIA, TEVC, MDPI SIs etc.) Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 30/ 40
  • 31. Abstract NLP UGPP CI References Some More Benchmark Function Sets The Genetic and Evolutionary Computation Conference (GECCO): I GECCO 2014 Windfarm Layout Optimization Competition I GECCO 2014 Permutation-based Combinatorial Optimization Problems I GECCO 2015 Black Box Optimization (BBComp) I GECCO 2015 Combinatorial Black-Box Optimization (CBBOC) I GECCO 2019 Workshop Competition on Numerical Optimization I Swarm and Evolutionary Computation: Novel benchmark functions for continuous multimodal optimization with comparative results (2015) I Benchmarks for natural architecture design: Spatial Tree Morphology Reconstruction (seeded/pre-processed/vectorized/multi-objective) I We prepare benchmarks for ocean exploration with underwater robots: Underwater Glider Path Planning (unconstraint/constraint/variable/multi-objective) Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 31/ 40
  • 32. Abstract NLP UGPP CI References Real World Industry Challenges: Motivation I Optimization of Real World Industry Challenges (RWIC), I selected as CEC 2011 Real World Optimization Problems, I a benchmark set contains functions modelling the problems, I assessment on all 22 functions of CEC 2011 set, I functions with constraints are handled with additional care. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 32/ 40
  • 33. Abstract NLP UGPP CI References Selected Challenges in the CEC 2011 Benchmark (1/2) I Decomposition of radio FM signals, I determination of ternary protein structure I Lennard-Jones inter-atom energy potential, I parameterization of a chemical process, I methylcyclopentane → benzene, I control parameterization for chemical reaction in a continuous stirred tank reactor, I inter-atom potential in covalent Silicon systems I Tersoff energy potential, I radar spectrum signal broadcast parameterization, I spread spectrum radar polly phase code design, I electrical transmission network expansion planning, I new lines for transmission selection. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 33/ 40
  • 34. Abstract NLP UGPP CI References Selected Challenges in the CEC 2011 Benchmark (2/2) I Large scale transmission pricing, I circular antenna array design, I dynamic economic dispatch (with power generator control), I static economic load dispatch (of power generated), I hydrothermal scheduling (among hydro/thermal units), I spacecraft trajectory optimization, I Mercury (Messenger), I Saturn (Cassini). I The collection includes 22 functions, with constraints as: 1. non-feasible evaluation is NaN when constraints are not met, or 2. the constraints are included in the function evaluation value. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 34/ 40
  • 35. Abstract NLP UGPP CI References Conclusion: Summary Teaching towards HPC Summary: presented 3 HPC domains (NLP, UGPP, CI). More: at University of Maribor, Bologna study courses for learning (teaching, training) of Computer Science at cycles — click URL: I level 1 (BSc) I year 1: Programming I – e.g. C++ syntax I year 2: Computer Architectures – e.g. assembly, microcode, ILP I year 3: Parallell and Distributed Computing – e.g. OpenMP, MPI, CUDA I level 2 (MSc) I year 1: Cloud Computing Deployment and Management – e.g. arc, slurm, containers (docker, singularity, kubernetes) I level 3 (PhD) I EU and other national projects research: HPC RIVR, EuroCC, DAPHNE, ... – e.g. scaling new systems of CI Operational Research of ... over HPC I IEEE Computational Intelligence Task Force on Benchmarking I Scientific Journals (e.g. SWEVO, TEVC, JoCS, ASOC, INS) These contribute towards Sustainable Development of HPC. Thanks! Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 35/ 40
  • 36. Abstract NLP UGPP CI References Biography and References: Organizations I Associate Professorat University of Maribor, Slovenia I Continuous research programme funded by Slovenian Research Agency, P2-0041: Computer Systems, Methodologies, and Intelligent Services I Associate Editor: Swarm and Evolutionary Computation (SWEVO) I IEEE (Institute of Electrical and Electronics Engineers) senior I IEEE Computational Intelligence Society (CIS), senior member I IEEE CIS Task Force on Benchmarking, chair I IEEE CIS, Slovenia Section Chapter (CH08873), chair I IEEE Slovenia Section, vice chair I IEEE Young Professionals Slovenia, past chair I ACM SIGEVO (Special Interest Group on Genetic and Evolutionary Computation); EurAI; SLAIS I Co-operation in Science and Techology (COST) Association Management Committee, member: I CA COST Action CA15140: Improving Applicability of Nature-Inspired Optimisation by Joining Theory and Practice (ImAppNIO), WG3 VC I ICT COST Action IC1406 High-Performance Modelling and Simulation for Big Data Applications (cHiPSet); SI-HPC; HPC-RIVR user I EU H2020 Research and Innovation project, holder for UM part: Integrated Data Analysis Pipelines for Large-Scale Data Management, HPC, and Machine Learning (DAPHNE), https://cordis.europa.eu/project/id/957407 Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 36/ 40
  • 37. Abstract NLP UGPP CI References Biography and References: Top Publications I Aleš Zamuda, Elena Lloret. Optimizing Data-Driven Models for Summarization as Parallel Tasks. Journal of Computational Science, 2020, vol. 42, pp. 101101. DOI 10.1016/j.jocs.2020.101101. I A. Zamuda, J. D. Hernández Sosa. Success history applied to expert system for underwater glider path planning using differential evolution. Expert Systems with Applications, 2019, vol. 119, pp. 155-170. DOI 10.1016/j.eswa.2018.10.048 I A. Viktorin, R. Senkerik, M. Pluhacek, T. Kadavy, A. Zamuda. Distance Based Parameter Adaptation for Success-History based Differential Evolution. Swarm and Evolutionary Computation, 2019, vol. 50, pp. 100462. DOI 10.1016/j.swevo.2018.10.013. I A. Zamuda, J. Brest. Self-adaptive control parameters’ randomization frequency and propagations in differential evolution. Swarm and Evolutionary Computation, 2015, vol. 25C, pp. 72-99. DOI 10.1016/j.swevo.2015.10.007. I A. Zamuda, J. D. Hernández Sosa, L. Adler. Constrained Differential Evolution Optimization for Underwater Glider Path Planning in Sub-mesoscale Eddy Sampling. Applied Soft Computing, 2016, vol. 42, pp. 93-118. DOI 10.1016/j.asoc.2016.01.038. I A. Zamuda, J. D. Hernández Sosa. Differential Evolution and Underwater Glider Path Planning Applied to the Short-Term Opportunistic Sampling of Dynamic Mesoscale Ocean Structures. Applied Soft Computing, vol. 24, November 2014, pp. 95-108. DOI 10.1016/j.asoc.2014.06.048. I A. Zamuda, J. Brest. Vectorized Procedural Models for Animated Trees Reconstruction using Differential Evolution. Information Sciences, vol. 278, pp. 1-21, 2014. DOI 10.1016/j.ins.2014.04.037. I A. Zamuda, J. Brest. Environmental Framework to Visualize Emergent Artificial Forest Ecosystems. Information Sciences, vol. 220, pp. 522-540, 2013. DOI 10.1016/j.ins.2012.07.031. I A. Glotić, A. Zamuda. Short-term combined economic and emission hydrothermal optimization by surrogate differential evolution. Applied Energy, 1 March 2015, vol. 141, pp. 42-56. DOI 10.1016/j.apenergy.2014.12.020. I H. Hamann, Y. Khaluf, J. Botev, M. Divband Soorati, E. Ferrante, O. Kosak, J.-M. Montanier, S. Mostaghim, R. Redpath, J. Timmis, F. Veenstra, M. Wahby and A. Zamuda. Hybrid Societies: Challenges and Perspectives in the Design of Collective Behavior in Self-organizing Systems. Frontiers in Robotics and AI, 2016, vol. 3, no. 14. DOI 10.3389/frobt.2016.00014. I J. Šilc, A. Zamuda. Special Issue on ”Bioinspired Optimization” (guest editors). Informatica - An International Journal of Computing and Informatics, 2015, vol. 39, no. 2, pp. 1-122. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 37/ 40
  • 38. Abstract NLP UGPP CI References Biography and References: Bound Specific to HPC PROJECTS: I DAPHNE: Integrated Data Analysis Pipelines for Large-Scale Data Management, HPC, and Machine Learning I ICT COST Action IC1406 High-Performance Modelling and Simulation for Big Data Applications I SLING: Slovenian national supercomputing network I SI-HPC: Slovenian corsortium for High-Performance Computing I UM HPC-RIVR: Supercomputer at UM, https://www.hpc-rivr.si/ I SmartVillages: Smart digital transformation of villages in the Alpine Space I Interreg Alpine Space, https://www.alpine-space.eu/projects/smartvillages/en/home I Interactive multimedia digital signage (PKP, Adin DS) EDITOR: I SWEVO (Top Journal), Associate Editor I Mathematics-MDPI, Special Issue: Evolutionary Algorithms in Engineering Design Optimization I Journal of advanced engineering and computation (member of editorial board since 2019). Viet Nam: Ton Duc Thang University, 2017-. ISSN 2588-123X. I Cloud Computing and Data Science (Associate Editor, since 2019). Universal Wiser Publisher Pte.Ltd. I D. Gleich, P. Planinšič, A. Zamuda. 2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP). IEEE Xplore, Maribor, 20-22 June 2018. I General Chair: 7-th Joint International Conferences on Swarm, Evolutionary and Memetic Computing Conference (SEMCCO 2019) Fuzzy And Neural Computing Conference (FANCCO 2019), Maribor, Slovenia, EU, 10-12 July 2019; co-editors: Aleš Zamuda, Swagatam Das, Ponnuthurai Nagaratnam Suganthan, Bijaya Ketan Panigrahi. Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 38/ 40
  • 39. Abstract NLP UGPP CI References Biography and References: More on HPC RESEARCH PUBLICATIONS: I Aleš Zamuda, Elena Lloret. Optimizing Data-Driven Models for Summarization as Parallel Tasks. Journal of Computational Science, 2020, vol. 42, pp. 101101. DOI 10.1016/j.jocs.2020.101101. I Aleš Zamuda, Vincenzo Crescimanna, Juan C. Burguillo, Joana Matos Dias, Katarzyna Wegrzyn-Wolska, Imen Rached, Horacio González-Vélez, Roman Senkerik, Claudia Pop, Tudor Cioara, Ioan Salomie, Andrea Bracciali. Forecasting Cryptocurrency Value by Sentiment Analysis: An HPC-Oriented Survey of the State-of-the-Art in the Cloud Era. Kolodziej J., González-Vélez H. (eds) High-Performance Modelling and Simulation for Big Data Applications. Lecture Notes in Computer Science, vol 11400, 2019, pp. 325-349. DOI 10.1007/978-3-030-16272-6 12. I Nenad Karolija, Aleš Zamuda. On cloud-supported web-based integrated development environment for programming dataflow architectures. MILUTINOVIĆ, Veljko (ur.), KOTLAR, Milos (ur.). Exploring the DataFlow supercomputing paradigm: example algorithms for selected applications, (Computer communications and networks (Internet), ISSN 2197-8433), 2019, pp. 41-51. DOI 10.1007/978-3-030-13803-5 2. I Simone Spolaor, Marco Gribaudo, Mauro Iacono, Tomas Kadavy, Zuzana Komı́nková Oplatková, Giancarlo Mauri, Sabri Pllana, Roman Senkerik, Natalija Stojanovic, Esko Turunen, Adam Viktorin, Salvatore Vitabile, Aleš Zamuda, Marco S. Nobile. Towards Human Cell Simulation. Kolodziej J., González-Vélez H. (eds) High-Performance Modelling and Simulation for Big Data Applications. Lecture Notes in Computer Science, vol 11400, 2019, pp. 221-249. DOI 10.1007/978-3-030-16272-6 8. I A. Zamuda, J. D. Hernandez Sosa, L. Adler. Improving Constrained Glider Trajectories for Ocean Eddy Border Sampling within Extended Mission Planning Time. IEEE Congress on Evolutionary Computation (CEC) 2016, 2016, pp. 1727-1734. I A. Zamuda. Function evaluations upto 1e+12 and large population sizes assessed in distance-based success history differential evolution for 100-digit challenge and numerical optimization scenarios (DISHchain 1e+12): a competition entry for ”100-digit challenge, and four other numerical optimization competitions” at the genetic and evolutionary computation conference (GECCO) 2019. Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO 2019), 2019, pp. 11-12. I ... several more experiments for papers run using HPCs. I ... also, pedagogic materials in Slovenian and English — see Conclusion . Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 39/ 40
  • 40. Abstract NLP UGPP CI References Promo materials: Calls for Papers, Informational Websites CS FERI WWW CIS TFoB CFPs WWW LinkedIn Twitter Aleš Zamuda 7@aleszamuda Parallelization of Benchmarking using HPC: NLP, UGPP CI 40/ 40