SlideShare uma empresa Scribd logo
1 de 59
Baixar para ler offline
Introduction Data systems @ scale Information selection Safety Conclusions
Data-driven challenges in AI:
scale, information selection, and safety
Anna Choromanska
New York University
ECE Department, Tandon Schoold of Engineering
Talk dedicated to my son, Marcin Tadeusz.
Introduction Data systems @ scale Information selection Safety Conclusions
Characteristics of modern data
Data size/multi-modality/safety
The amount of available digital data is doubling every two years; by 2020
the amount of data we create and copy annually will reach 44 zettabytes.
EMC Digital Universe study
Introduction Data systems @ scale Information selection Safety Conclusions
Characteristics of modern data
Data size/multi-modality/safety
The amount of available digital data is doubling every two years; by 2020
the amount of data we create and copy annually will reach 44 zettabytes.
EMC Digital Universe study
The data comes from multiple modalities such as LiDARs (point cloud),
cameras (images), natural language (text, speech), . . .
Introduction Data systems @ scale Information selection Safety Conclusions
Characteristics of modern data
Data size/multi-modality/safety
The amount of available digital data is doubling every two years; by 2020
the amount of data we create and copy annually will reach 44 zettabytes.
EMC Digital Universe study
The data comes from multiple modalities such as LiDARs (point cloud),
cameras (images), natural language (text, speech), . . .
Data can be safe or else anomalous/corrupted/adversarial.
Introduction Data systems @ scale Information selection Safety Conclusions
Challenges driven by modern data
Data-driven challenges in AI
scale: how to build AI systems @ scale?
Introduction Data systems @ scale Information selection Safety Conclusions
Challenges driven by modern data
Data-driven challenges in AI
scale: how to build AI systems @ scale?
information selection: how to
effectively process data
= choose relevant data modalities/portions
= avoid wasteful computations?
Introduction Data systems @ scale Information selection Safety Conclusions
Challenges driven by modern data
Data-driven challenges in AI
scale: how to build AI systems @ scale?
information selection: how to
effectively process data
= choose relevant data modalities/portions
= avoid wasteful computations?
safety: how to verify and trust the data?
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
eXtreme classification problem
Problem setting:
multi-class classification: each data point is assigned one label
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
eXtreme classification problem
Problem setting:
multi-class classification: each data point is assigned one label
multi-label classification: each data point is assigned a subset
of labels
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
eXtreme classification problem
Problem setting:
multi-class classification: each data point is assigned one label
multi-label classification: each data point is assigned a subset
of labels
Applications:
search engines
targeted advertising
aggregation of online news stories and their categorization
. . .
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
eXtreme classification problem
Problem setting:
multi-class classification: each data point is assigned one label
multi-label classification: each data point is assigned a subset
of labels
Goal: good predictor with logarithmic training and testing time
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
eXtreme classification problem
Problem setting:
multi-class classification: each data point is assigned one label
multi-label classification: each data point is assigned a subset
of labels
Goal: good predictor with logarithmic training and testing time
Most multi-class algo-
rithms run in O(k) time,
where k is the number of
classes. The lower-bound
is O(log k) .
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Tree-based classifier
h - hypothesis inducing the split, x - data point
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Tree-based classifier
h - hypothesis inducing the split, x - data point
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Pure and balanced split
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Pure and balanced split
Design per-node objective function that favors:
balanced splits ⇒ efficient tree
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Pure and balanced split
Design per-node objective function that favors:
balanced splits ⇒ efficient tree
pure splits ⇒ small classification error
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective function
J :=
M
j=1
M
l=j+1
|Pj −Pl |
balancing term
−λ1
K
y=1
M
j=1
M
l=j+1
πi Py
j −Py
l
class integrity term
+ λ2


M
j=1
Pj

−1
multi-way penalty
purity term
∈[−λ1, λ2]
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective function
J :=
M
j=1
M
l=j+1
|Pj −Pl |
balancing term
−λ1
K
y=1
M
j=1
M
l=j+1
πi Py
j −Py
l
class integrity term
+ λ2


M
j=1
Pj

−1
multi-way penalty
purity term
∈[−λ1, λ2]
J ⇒ Splitting criterion (objective function)
Given a set of n examples each with one (multi-class)/subset
(multi-label) of k labels, find a partitioner h that minimizes J.
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective function
J :=
M
j=1
M
l=j+1
|Pj −Pl |
balancing term
−λ1
K
y=1
M
j=1
M
l=j+1
πi Py
j −Py
l
class integrity term
+ λ2


M
j=1
Pj

−1
multi-way penalty
purity term
∈[−λ1, λ2]
J ⇒ Splitting criterion (objective function)
Given a set of n examples each with one (multi-class)/subset
(multi-label) of k labels, find a partitioner h that minimizes J.
Decreasing J leads to more pure and more balanced splits
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective function
J :=
M
j=1
M
l=j+1
|Pj −Pl |
balancing term
−λ1
K
y=1
M
j=1
M
l=j+1
πi Py
j −Py
l
class integrity term
+ λ2


M
j=1
Pj

−1
multi-way penalty
purity term
∈[−λ1, λ2]
J ⇒ Splitting criterion (objective function)
Given a set of n examples each with one (multi-class)/subset
(multi-label) of k labels, find a partitioner h that minimizes J.
Decreasing J leads to more pure and more balanced splits
⇒ efficient trees with logarithmic depth
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective function
J :=
M
j=1
M
l=j+1
|Pj −Pl |
balancing term
−λ1
K
y=1
M
j=1
M
l=j+1
πi Py
j −Py
l
class integrity term
+ λ2


M
j=1
Pj

−1
multi-way penalty
purity term
∈[−λ1, λ2]
J ⇒ Splitting criterion (objective function)
Given a set of n examples each with one (multi-class)/subset
(multi-label) of k labels, find a partitioner h that minimizes J.
Decreasing J leads to more pure and more balanced splits
⇒ efficient trees with logarithmic depth
Decreasing J leads to the reduction of the tree error
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective function
J :=
M
j=1
M
l=j+1
|Pj −Pl |
balancing term
−λ1
K
y=1
M
j=1
M
l=j+1
πi Py
j −Py
l
class integrity term
+ λ2


M
j=1
Pj

−1
multi-way penalty
purity term
∈[−λ1, λ2]
J ⇒ Splitting criterion (objective function)
Given a set of n examples each with one (multi-class)/subset
(multi-label) of k labels, find a partitioner h that minimizes J.
Decreasing J leads to more pure and more balanced splits
⇒ efficient trees with logarithmic depth
Decreasing J leads to the reduction of the tree error
⇒ small-error trees
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective properties
J extends to trees of arbitrary arity
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective properties
J extends to trees of arbitrary arity
J can be easily optimized with SGD
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective properties
J extends to trees of arbitrary arity
J can be easily optimized with SGD
J leads to the algorithm for tree construction and training
that runs online
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective properties
J extends to trees of arbitrary arity
J can be easily optimized with SGD
J leads to the algorithm for tree construction and training
that runs online
The approach accommodates classification as well as density
estimation problems.
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Objective properties
J extends to trees of arbitrary arity
J can be easily optimized with SGD
J leads to the algorithm for tree construction and training
that runs online
The approach accommodates classification as well as density
estimation problems.
J can be used to learn both the label partitioning and the
data representation simultaneously!
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Deep eXtreme classification
Deep representation learning:
Computation in the last layer can blow up...
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Deep eXtreme classification
Deep representation learning:
Computation in the last layer can blow up...
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Deep eXtreme classification
Deep representation learning:
Computation in the last layer can blow up...
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Experiments: classification
Table: Precisions: P@1, P@3, and P@5 (%) and nDCG scores: N@1,
N@3, and N@5 (%) obtained by OAA, LPSR, FastXML, PFastreXML,
and LdSM (d,M) with the depth of the tree d and arity M.
Delicious-200k N = 197k, D = 783k, K = 205k
Algorithm P@1 P@3 P@5 N@1 N@3 N@5
LPSR 18.59 15.43 14.07 18.59 16.17 15.13
FastXML 43.07 38.66 36.19 43.07 39.70 37.83
PFastreXML 41.72 37.83 35.58 41.72 38.76 37.08
LdSM (35,2) 43.40 39.80 37.75 43.40 40.66 39.11
Introduction Data systems @ scale Information selection Safety Conclusions
eXtreme classification
Experiments: classification
Table: Precisions: P@1, P@3, and P@5 (%) and nDCG scores: N@1,
N@3, and N@5 (%) obtained by OAA, LPSR, FastXML, PFastreXML,
and LdSM (d,M) with the depth of the tree d and arity M.
Delicious-200k N = 197k, D = 783k, K = 205k
Algorithm P@1 P@3 P@5 N@1 N@3 N@5
LPSR 18.59 15.43 14.07 18.59 16.17 15.13
FastXML 43.07 38.66 36.19 43.07 39.70 37.83
PFastreXML 41.72 37.83 35.58 41.72 38.76 37.08
LdSM (35,2) 43.40 39.80 37.75 43.40 40.66 39.11
Table: Prediction time [ms] per example for FastXML, PFastreXML, and
LdSM on AmazonCat, Wiki10, and Delicious-200k data sets.
FastXML PFastreXML LdSM
AmazonCat 1.21 1.34 0.49
Wiki10 3.00 NA 1.21
Delicious-200k 1.28 7.40 1.30
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
steering command: the only available supervision
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
steering command: the only available supervision
Goal:
avoid fast increase of computational complexity with the
number of sensing devices
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
steering command: the only available supervision
Goal:
avoid fast increase of computational complexity with the
number of sensing devices
activate feature extractors for relevant inputs only
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
steering command: the only available supervision
Goal:
avoid fast increase of computational complexity with the
number of sensing devices
activate feature extractors for relevant inputs only
avoid overfitting to the simplest and most informative input
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
steering command: the only available supervision
Goal:
avoid fast increase of computational complexity with the
number of sensing devices
activate feature extractors for relevant inputs only
avoid overfitting to the simplest and most informative input
guarantee real-time operation
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Sensor selection problem for autonomous driving
Problem setting:
autonomous car equipped with multiple sensors
end-to-end training framework
steering command: the only available supervision
Goal:
avoid fast increase of computational complexity with the
number of sensing devices
activate feature extractors for relevant inputs only
avoid overfitting to the simplest and most informative input
guarantee real-time operation
allow both discrete and continuous data selection
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Hardware
Figure: The block diagram of the autonomous platform.
Traxxas X-Maxx remote control truck (RC car, scale 1/6)
DrivePX2 for computations
three SEKONIX AR0231 GMSL cameras that are facing the
front of the platform and cover non-overlapping views. Each
camera has 60 degrees horizontal field of view
Velodyne VLP-16 LiDAR with 16 lasers covering 30 degree
vertical FOV and 360 degree horizontal FOV
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Approach: multi-modality and mixed policy
Figure: The architecture of the reconfigurable network.
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Approach: multi-modality and mixed policy
Figure: Different stages of training.
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Experiments: multi-modality and mixed policy
Table: Computational complexity comparison of different networks.
Network Name FLOPs
LiDAR only 26.17M
LiDAR with gating 14.11M
Single Camera 25.38M
Three Cameras 76.01M
Three cameras and LiDAR 102.49M
Three cameras and LiDAR with gating 90.08M
Multi-modal Experts Network 17.28M
chosen sensor: LiDAR
Multi-modal Experts Network 29.61M
chosen sensor: camera
Introduction Data systems @ scale Information selection Safety Conclusions
Sensor selection for autonomous driving
Experiments: multi-modality and mixed policy
Introduction Data systems @ scale Information selection Safety Conclusions
Safety in autonomous driving
Problem of safety in autonomous driving
Problem setting:
autonomous car instrumented with cameras and LIDAR and
controlled by an end-to-end learning system
Introduction Data systems @ scale Information selection Safety Conclusions
Safety in autonomous driving
Problem of safety in autonomous driving
Problem setting:
autonomous car instrumented with cameras and LIDAR and
controlled by an end-to-end learning system
Goal:
develop on-line monitoring framework for continuous real-time
safety in learning-based control systems
Introduction Data systems @ scale Information selection Safety Conclusions
Safety in autonomous driving
Problem of safety in autonomous driving
Problem setting:
autonomous car instrumented with cameras and LIDAR and
controlled by an end-to-end learning system
Goal:
develop on-line monitoring framework for continuous real-time
safety in learning-based control systems
monitor the validity of mappings from sensor inputs to
actuator commands
Introduction Data systems @ scale Information selection Safety Conclusions
Safety in autonomous driving
CEBGAN for safety in autonomous driving
Figure: Conditional energy based generative adversarial network
(CEBGAN) framework for the controller-focused anomaly detection
(CFAM).
Introduction Data systems @ scale Information selection Safety Conclusions
Safety in autonomous driving
Experiments
Figure: Safe operation of the autonomous platform.
Figure: Anomalous operation of the autonomous platform.
Introduction Data systems @ scale Information selection Safety Conclusions
Safety in autonomous driving
Experiments
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
Summary and Future Directions
Discussed approaches:
scale: using decisions trees to scale AI systems to large data
sizes
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
Summary and Future Directions
Discussed approaches:
scale: using decisions trees to scale AI systems to large data
sizes
information selection: using reconfigurable networks to select
relevant data
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
Summary and Future Directions
Discussed approaches:
scale: using decisions trees to scale AI systems to large data
sizes
information selection: using reconfigurable networks to select
relevant data
safety: using GANs to monitor system’s safety
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
Summary and Future Directions
Discussed approaches:
scale: using decisions trees to scale AI systems to large data
sizes
information selection: using reconfigurable networks to select
relevant data
safety: using GANs to monitor system’s safety
Future directions:
logarithmic space framework, modern recommendation
systems, other applications
scaling information selection algorithms to a large number of
inputs
ambiguous scenarios, increasing system’s robustness
practical sample complexity bounds
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
Research Group
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
Research Group
Many thanks to NVIDIA Autonomous Driving
Team in New Jersey!!!
Introduction Data systems @ scale Information selection Safety Conclusions
Summary
NYU Tandon ECE Seminar Series on Modern AI
DOORS ARE OPEN TO EVERYBODY!!!
Past Speakers: Yann LeCun, Yoshua Bengio, Stefano Soatto,
Vladimir Vapnik, David Blei, Richard J. Roberts, Anima
Anadkumar, Martial Hebert, Tony Jebara
Future confirmed speakers: Manuela Veloso, Eric Kandel, Francis
Bach, Raia Hadsell, Leon Bottou, Michael Kearns, Nicol`o
Cesa-Bianchi

Mais conteúdo relacionado

Mais procurados

IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
ijceronline
 
Ppback propagation-bansal-zhong-2010
Ppback propagation-bansal-zhong-2010Ppback propagation-bansal-zhong-2010
Ppback propagation-bansal-zhong-2010
girivaishali
 
Neural Network Classification and its Applications in Insurance Industry
Neural Network Classification and its Applications in Insurance IndustryNeural Network Classification and its Applications in Insurance Industry
Neural Network Classification and its Applications in Insurance Industry
Inderjeet Singh
 
Presentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data MiningPresentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data Mining
butest
 
Test PDF
Test PDFTest PDF
Test PDF
AlgnuD
 

Mais procurados (20)

Survey on evolutionary computation tech techniques and its application in dif...
Survey on evolutionary computation tech techniques and its application in dif...Survey on evolutionary computation tech techniques and its application in dif...
Survey on evolutionary computation tech techniques and its application in dif...
 
Research scholars evaluation based on guides view
Research scholars evaluation based on guides viewResearch scholars evaluation based on guides view
Research scholars evaluation based on guides view
 
IRE Semantic Annotation of Documents
IRE Semantic Annotation of Documents IRE Semantic Annotation of Documents
IRE Semantic Annotation of Documents
 
IRJET - House Price Predictor using ML through Artificial Neural Network
IRJET - House Price Predictor using ML through Artificial Neural NetworkIRJET - House Price Predictor using ML through Artificial Neural Network
IRJET - House Price Predictor using ML through Artificial Neural Network
 
Research scholars evaluation based on guides view using id3
Research scholars evaluation based on guides view using id3Research scholars evaluation based on guides view using id3
Research scholars evaluation based on guides view using id3
 
Data mining weka
Data mining wekaData mining weka
Data mining weka
 
ANALYSIS AND COMPARISON STUDY OF DATA MINING ALGORITHMS USING RAPIDMINER
ANALYSIS AND COMPARISON STUDY OF DATA MINING ALGORITHMS USING RAPIDMINERANALYSIS AND COMPARISON STUDY OF DATA MINING ALGORITHMS USING RAPIDMINER
ANALYSIS AND COMPARISON STUDY OF DATA MINING ALGORITHMS USING RAPIDMINER
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
Ppback propagation-bansal-zhong-2010
Ppback propagation-bansal-zhong-2010Ppback propagation-bansal-zhong-2010
Ppback propagation-bansal-zhong-2010
 
Neural Network Classification and its Applications in Insurance Industry
Neural Network Classification and its Applications in Insurance IndustryNeural Network Classification and its Applications in Insurance Industry
Neural Network Classification and its Applications in Insurance Industry
 
Multimedia data mining using deep learning
Multimedia data mining using deep learningMultimedia data mining using deep learning
Multimedia data mining using deep learning
 
G44093135
G44093135G44093135
G44093135
 
Presentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data MiningPresentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data Mining
 
IRJET- Student Placement Prediction using Machine Learning
IRJET- Student Placement Prediction using Machine LearningIRJET- Student Placement Prediction using Machine Learning
IRJET- Student Placement Prediction using Machine Learning
 
Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...
Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...
Identification of Brain Regions Related to Alzheimers' Diseases using MRI Ima...
 
Test PDF
Test PDFTest PDF
Test PDF
 
5.local community detection algorithm based on minimal cluster
5.local community detection algorithm based on minimal cluster5.local community detection algorithm based on minimal cluster
5.local community detection algorithm based on minimal cluster
 
Intrusion Detection System for Classification of Attacks with Cross Validation
Intrusion Detection System for Classification of Attacks with Cross ValidationIntrusion Detection System for Classification of Attacks with Cross Validation
Intrusion Detection System for Classification of Attacks with Cross Validation
 
SAM 40
SAM 40SAM 40
SAM 40
 
Identification of Relevant Sections in Web Pages Using a Machine Learning App...
Identification of Relevant Sections in Web Pages Using a Machine Learning App...Identification of Relevant Sections in Web Pages Using a Machine Learning App...
Identification of Relevant Sections in Web Pages Using a Machine Learning App...
 

Semelhante a Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection, and Safety

Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...
Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...
Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...
ShivarkarSandip
 
slides
slidesslides
slides
butest
 
Classification (ML).ppt
Classification (ML).pptClassification (ML).ppt
Classification (ML).ppt
rajasamal1999
 
DSA 1- Introduction.pdf
DSA 1- Introduction.pdfDSA 1- Introduction.pdf
DSA 1- Introduction.pdf
AliyanAbbas1
 

Semelhante a Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection, and Safety (20)

Data Science Full Course | Edureka
Data Science Full Course | EdurekaData Science Full Course | Edureka
Data Science Full Course | Edureka
 
2.2 decision tree
2.2 decision tree2.2 decision tree
2.2 decision tree
 
Classfication Basic.ppt
Classfication Basic.pptClassfication Basic.ppt
Classfication Basic.ppt
 
IRJET- A Data Mining with Big Data Disease Prediction
IRJET-  	  A Data Mining with Big Data Disease PredictionIRJET-  	  A Data Mining with Big Data Disease Prediction
IRJET- A Data Mining with Big Data Disease Prediction
 
Water Quality Index Calculation of River Ganga using Decision Tree Algorithm
Water Quality Index Calculation of River Ganga using Decision Tree AlgorithmWater Quality Index Calculation of River Ganga using Decision Tree Algorithm
Water Quality Index Calculation of River Ganga using Decision Tree Algorithm
 
Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...
Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...
Classification, Attribute Selection, Classifiers- Decision Tree, ID3,C4.5,Nav...
 
slides
slidesslides
slides
 
Introduction to Data Mining
Introduction to Data MiningIntroduction to Data Mining
Introduction to Data Mining
 
IRJET- Study and Evaluation of Classification Algorithms in Data Mining
IRJET- Study and Evaluation of Classification Algorithms in Data MiningIRJET- Study and Evaluation of Classification Algorithms in Data Mining
IRJET- Study and Evaluation of Classification Algorithms in Data Mining
 
Using AA for incident classification
Using AA for incident classificationUsing AA for incident classification
Using AA for incident classification
 
unit 5 decision tree2.pptx
unit 5 decision tree2.pptxunit 5 decision tree2.pptx
unit 5 decision tree2.pptx
 
Machine learning
Machine learningMachine learning
Machine learning
 
Decision tree
Decision treeDecision tree
Decision tree
 
Classification (ML).ppt
Classification (ML).pptClassification (ML).ppt
Classification (ML).ppt
 
DSA 1- Introduction.pdf
DSA 1- Introduction.pdfDSA 1- Introduction.pdf
DSA 1- Introduction.pdf
 
NETWORJS3.pdf
NETWORJS3.pdfNETWORJS3.pdf
NETWORJS3.pdf
 
Workshop nwav 47 - LVS - Tool for Quantitative Data Analysis
Workshop nwav 47 - LVS - Tool for Quantitative Data AnalysisWorkshop nwav 47 - LVS - Tool for Quantitative Data Analysis
Workshop nwav 47 - LVS - Tool for Quantitative Data Analysis
 
IRJET- Performance Evaluation of Various Classification Algorithms
IRJET- Performance Evaluation of Various Classification AlgorithmsIRJET- Performance Evaluation of Various Classification Algorithms
IRJET- Performance Evaluation of Various Classification Algorithms
 
IRJET- Performance Evaluation of Various Classification Algorithms
IRJET- Performance Evaluation of Various Classification AlgorithmsIRJET- Performance Evaluation of Various Classification Algorithms
IRJET- Performance Evaluation of Various Classification Algorithms
 
Machine Learning ebook.pdf
Machine Learning ebook.pdfMachine Learning ebook.pdf
Machine Learning ebook.pdf
 

Mais de MLconf

Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
MLconf
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
MLconf
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
MLconf
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
MLconf
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI World
MLconf
 

Mais de MLconf (20)

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
 
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushIgor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
 
Josh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceJosh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious Experience
 
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
 
Meghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMeghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the Cheap
 
Noam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionNoam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data Collection
 
June Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLJune Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of ML
 
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksSneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI World
 
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
 
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
 
Neel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeNeel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to code
 
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
 
Soumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareSoumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better Software
 
Roy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesRoy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime Changes
 
Madalina Fiterau - Hybrid Machine Learning Methods for the Interpretation and...
Madalina Fiterau - Hybrid Machine Learning Methods for the Interpretation and...Madalina Fiterau - Hybrid Machine Learning Methods for the Interpretation and...
Madalina Fiterau - Hybrid Machine Learning Methods for the Interpretation and...
 

Último

EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 

Último (20)

Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdf
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 

Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection, and Safety

  • 1. Introduction Data systems @ scale Information selection Safety Conclusions Data-driven challenges in AI: scale, information selection, and safety Anna Choromanska New York University ECE Department, Tandon Schoold of Engineering Talk dedicated to my son, Marcin Tadeusz.
  • 2. Introduction Data systems @ scale Information selection Safety Conclusions Characteristics of modern data Data size/multi-modality/safety The amount of available digital data is doubling every two years; by 2020 the amount of data we create and copy annually will reach 44 zettabytes. EMC Digital Universe study
  • 3. Introduction Data systems @ scale Information selection Safety Conclusions Characteristics of modern data Data size/multi-modality/safety The amount of available digital data is doubling every two years; by 2020 the amount of data we create and copy annually will reach 44 zettabytes. EMC Digital Universe study The data comes from multiple modalities such as LiDARs (point cloud), cameras (images), natural language (text, speech), . . .
  • 4. Introduction Data systems @ scale Information selection Safety Conclusions Characteristics of modern data Data size/multi-modality/safety The amount of available digital data is doubling every two years; by 2020 the amount of data we create and copy annually will reach 44 zettabytes. EMC Digital Universe study The data comes from multiple modalities such as LiDARs (point cloud), cameras (images), natural language (text, speech), . . . Data can be safe or else anomalous/corrupted/adversarial.
  • 5. Introduction Data systems @ scale Information selection Safety Conclusions Challenges driven by modern data Data-driven challenges in AI scale: how to build AI systems @ scale?
  • 6. Introduction Data systems @ scale Information selection Safety Conclusions Challenges driven by modern data Data-driven challenges in AI scale: how to build AI systems @ scale? information selection: how to effectively process data = choose relevant data modalities/portions = avoid wasteful computations?
  • 7. Introduction Data systems @ scale Information selection Safety Conclusions Challenges driven by modern data Data-driven challenges in AI scale: how to build AI systems @ scale? information selection: how to effectively process data = choose relevant data modalities/portions = avoid wasteful computations? safety: how to verify and trust the data?
  • 8. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification eXtreme classification problem Problem setting: multi-class classification: each data point is assigned one label
  • 9. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification eXtreme classification problem Problem setting: multi-class classification: each data point is assigned one label multi-label classification: each data point is assigned a subset of labels
  • 10. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification eXtreme classification problem Problem setting: multi-class classification: each data point is assigned one label multi-label classification: each data point is assigned a subset of labels Applications: search engines targeted advertising aggregation of online news stories and their categorization . . .
  • 11. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification eXtreme classification problem Problem setting: multi-class classification: each data point is assigned one label multi-label classification: each data point is assigned a subset of labels Goal: good predictor with logarithmic training and testing time
  • 12. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification eXtreme classification problem Problem setting: multi-class classification: each data point is assigned one label multi-label classification: each data point is assigned a subset of labels Goal: good predictor with logarithmic training and testing time Most multi-class algo- rithms run in O(k) time, where k is the number of classes. The lower-bound is O(log k) .
  • 13. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Tree-based classifier h - hypothesis inducing the split, x - data point
  • 14. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Tree-based classifier h - hypothesis inducing the split, x - data point
  • 15. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Pure and balanced split
  • 16. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Pure and balanced split Design per-node objective function that favors: balanced splits ⇒ efficient tree
  • 17. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Pure and balanced split Design per-node objective function that favors: balanced splits ⇒ efficient tree pure splits ⇒ small classification error
  • 18. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective function J := M j=1 M l=j+1 |Pj −Pl | balancing term −λ1 K y=1 M j=1 M l=j+1 πi Py j −Py l class integrity term + λ2   M j=1 Pj  −1 multi-way penalty purity term ∈[−λ1, λ2]
  • 19. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective function J := M j=1 M l=j+1 |Pj −Pl | balancing term −λ1 K y=1 M j=1 M l=j+1 πi Py j −Py l class integrity term + λ2   M j=1 Pj  −1 multi-way penalty purity term ∈[−λ1, λ2] J ⇒ Splitting criterion (objective function) Given a set of n examples each with one (multi-class)/subset (multi-label) of k labels, find a partitioner h that minimizes J.
  • 20. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective function J := M j=1 M l=j+1 |Pj −Pl | balancing term −λ1 K y=1 M j=1 M l=j+1 πi Py j −Py l class integrity term + λ2   M j=1 Pj  −1 multi-way penalty purity term ∈[−λ1, λ2] J ⇒ Splitting criterion (objective function) Given a set of n examples each with one (multi-class)/subset (multi-label) of k labels, find a partitioner h that minimizes J. Decreasing J leads to more pure and more balanced splits
  • 21. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective function J := M j=1 M l=j+1 |Pj −Pl | balancing term −λ1 K y=1 M j=1 M l=j+1 πi Py j −Py l class integrity term + λ2   M j=1 Pj  −1 multi-way penalty purity term ∈[−λ1, λ2] J ⇒ Splitting criterion (objective function) Given a set of n examples each with one (multi-class)/subset (multi-label) of k labels, find a partitioner h that minimizes J. Decreasing J leads to more pure and more balanced splits ⇒ efficient trees with logarithmic depth
  • 22. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective function J := M j=1 M l=j+1 |Pj −Pl | balancing term −λ1 K y=1 M j=1 M l=j+1 πi Py j −Py l class integrity term + λ2   M j=1 Pj  −1 multi-way penalty purity term ∈[−λ1, λ2] J ⇒ Splitting criterion (objective function) Given a set of n examples each with one (multi-class)/subset (multi-label) of k labels, find a partitioner h that minimizes J. Decreasing J leads to more pure and more balanced splits ⇒ efficient trees with logarithmic depth Decreasing J leads to the reduction of the tree error
  • 23. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective function J := M j=1 M l=j+1 |Pj −Pl | balancing term −λ1 K y=1 M j=1 M l=j+1 πi Py j −Py l class integrity term + λ2   M j=1 Pj  −1 multi-way penalty purity term ∈[−λ1, λ2] J ⇒ Splitting criterion (objective function) Given a set of n examples each with one (multi-class)/subset (multi-label) of k labels, find a partitioner h that minimizes J. Decreasing J leads to more pure and more balanced splits ⇒ efficient trees with logarithmic depth Decreasing J leads to the reduction of the tree error ⇒ small-error trees
  • 24. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective properties J extends to trees of arbitrary arity
  • 25. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective properties J extends to trees of arbitrary arity J can be easily optimized with SGD
  • 26. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective properties J extends to trees of arbitrary arity J can be easily optimized with SGD J leads to the algorithm for tree construction and training that runs online
  • 27. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective properties J extends to trees of arbitrary arity J can be easily optimized with SGD J leads to the algorithm for tree construction and training that runs online The approach accommodates classification as well as density estimation problems.
  • 28. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Objective properties J extends to trees of arbitrary arity J can be easily optimized with SGD J leads to the algorithm for tree construction and training that runs online The approach accommodates classification as well as density estimation problems. J can be used to learn both the label partitioning and the data representation simultaneously!
  • 29. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Deep eXtreme classification Deep representation learning: Computation in the last layer can blow up...
  • 30. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Deep eXtreme classification Deep representation learning: Computation in the last layer can blow up...
  • 31. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Deep eXtreme classification Deep representation learning: Computation in the last layer can blow up...
  • 32. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Experiments: classification Table: Precisions: P@1, P@3, and P@5 (%) and nDCG scores: N@1, N@3, and N@5 (%) obtained by OAA, LPSR, FastXML, PFastreXML, and LdSM (d,M) with the depth of the tree d and arity M. Delicious-200k N = 197k, D = 783k, K = 205k Algorithm P@1 P@3 P@5 N@1 N@3 N@5 LPSR 18.59 15.43 14.07 18.59 16.17 15.13 FastXML 43.07 38.66 36.19 43.07 39.70 37.83 PFastreXML 41.72 37.83 35.58 41.72 38.76 37.08 LdSM (35,2) 43.40 39.80 37.75 43.40 40.66 39.11
  • 33. Introduction Data systems @ scale Information selection Safety Conclusions eXtreme classification Experiments: classification Table: Precisions: P@1, P@3, and P@5 (%) and nDCG scores: N@1, N@3, and N@5 (%) obtained by OAA, LPSR, FastXML, PFastreXML, and LdSM (d,M) with the depth of the tree d and arity M. Delicious-200k N = 197k, D = 783k, K = 205k Algorithm P@1 P@3 P@5 N@1 N@3 N@5 LPSR 18.59 15.43 14.07 18.59 16.17 15.13 FastXML 43.07 38.66 36.19 43.07 39.70 37.83 PFastreXML 41.72 37.83 35.58 41.72 38.76 37.08 LdSM (35,2) 43.40 39.80 37.75 43.40 40.66 39.11 Table: Prediction time [ms] per example for FastXML, PFastreXML, and LdSM on AmazonCat, Wiki10, and Delicious-200k data sets. FastXML PFastreXML LdSM AmazonCat 1.21 1.34 0.49 Wiki10 3.00 NA 1.21 Delicious-200k 1.28 7.40 1.30
  • 34. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors
  • 35. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework
  • 36. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework steering command: the only available supervision
  • 37. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework steering command: the only available supervision Goal: avoid fast increase of computational complexity with the number of sensing devices
  • 38. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework steering command: the only available supervision Goal: avoid fast increase of computational complexity with the number of sensing devices activate feature extractors for relevant inputs only
  • 39. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework steering command: the only available supervision Goal: avoid fast increase of computational complexity with the number of sensing devices activate feature extractors for relevant inputs only avoid overfitting to the simplest and most informative input
  • 40. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework steering command: the only available supervision Goal: avoid fast increase of computational complexity with the number of sensing devices activate feature extractors for relevant inputs only avoid overfitting to the simplest and most informative input guarantee real-time operation
  • 41. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Sensor selection problem for autonomous driving Problem setting: autonomous car equipped with multiple sensors end-to-end training framework steering command: the only available supervision Goal: avoid fast increase of computational complexity with the number of sensing devices activate feature extractors for relevant inputs only avoid overfitting to the simplest and most informative input guarantee real-time operation allow both discrete and continuous data selection
  • 42. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Hardware Figure: The block diagram of the autonomous platform. Traxxas X-Maxx remote control truck (RC car, scale 1/6) DrivePX2 for computations three SEKONIX AR0231 GMSL cameras that are facing the front of the platform and cover non-overlapping views. Each camera has 60 degrees horizontal field of view Velodyne VLP-16 LiDAR with 16 lasers covering 30 degree vertical FOV and 360 degree horizontal FOV
  • 43. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Approach: multi-modality and mixed policy Figure: The architecture of the reconfigurable network.
  • 44. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Approach: multi-modality and mixed policy Figure: Different stages of training.
  • 45. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Experiments: multi-modality and mixed policy Table: Computational complexity comparison of different networks. Network Name FLOPs LiDAR only 26.17M LiDAR with gating 14.11M Single Camera 25.38M Three Cameras 76.01M Three cameras and LiDAR 102.49M Three cameras and LiDAR with gating 90.08M Multi-modal Experts Network 17.28M chosen sensor: LiDAR Multi-modal Experts Network 29.61M chosen sensor: camera
  • 46. Introduction Data systems @ scale Information selection Safety Conclusions Sensor selection for autonomous driving Experiments: multi-modality and mixed policy
  • 47. Introduction Data systems @ scale Information selection Safety Conclusions Safety in autonomous driving Problem of safety in autonomous driving Problem setting: autonomous car instrumented with cameras and LIDAR and controlled by an end-to-end learning system
  • 48. Introduction Data systems @ scale Information selection Safety Conclusions Safety in autonomous driving Problem of safety in autonomous driving Problem setting: autonomous car instrumented with cameras and LIDAR and controlled by an end-to-end learning system Goal: develop on-line monitoring framework for continuous real-time safety in learning-based control systems
  • 49. Introduction Data systems @ scale Information selection Safety Conclusions Safety in autonomous driving Problem of safety in autonomous driving Problem setting: autonomous car instrumented with cameras and LIDAR and controlled by an end-to-end learning system Goal: develop on-line monitoring framework for continuous real-time safety in learning-based control systems monitor the validity of mappings from sensor inputs to actuator commands
  • 50. Introduction Data systems @ scale Information selection Safety Conclusions Safety in autonomous driving CEBGAN for safety in autonomous driving Figure: Conditional energy based generative adversarial network (CEBGAN) framework for the controller-focused anomaly detection (CFAM).
  • 51. Introduction Data systems @ scale Information selection Safety Conclusions Safety in autonomous driving Experiments Figure: Safe operation of the autonomous platform. Figure: Anomalous operation of the autonomous platform.
  • 52. Introduction Data systems @ scale Information selection Safety Conclusions Safety in autonomous driving Experiments
  • 53. Introduction Data systems @ scale Information selection Safety Conclusions Summary Summary and Future Directions Discussed approaches: scale: using decisions trees to scale AI systems to large data sizes
  • 54. Introduction Data systems @ scale Information selection Safety Conclusions Summary Summary and Future Directions Discussed approaches: scale: using decisions trees to scale AI systems to large data sizes information selection: using reconfigurable networks to select relevant data
  • 55. Introduction Data systems @ scale Information selection Safety Conclusions Summary Summary and Future Directions Discussed approaches: scale: using decisions trees to scale AI systems to large data sizes information selection: using reconfigurable networks to select relevant data safety: using GANs to monitor system’s safety
  • 56. Introduction Data systems @ scale Information selection Safety Conclusions Summary Summary and Future Directions Discussed approaches: scale: using decisions trees to scale AI systems to large data sizes information selection: using reconfigurable networks to select relevant data safety: using GANs to monitor system’s safety Future directions: logarithmic space framework, modern recommendation systems, other applications scaling information selection algorithms to a large number of inputs ambiguous scenarios, increasing system’s robustness practical sample complexity bounds
  • 57. Introduction Data systems @ scale Information selection Safety Conclusions Summary Research Group
  • 58. Introduction Data systems @ scale Information selection Safety Conclusions Summary Research Group Many thanks to NVIDIA Autonomous Driving Team in New Jersey!!!
  • 59. Introduction Data systems @ scale Information selection Safety Conclusions Summary NYU Tandon ECE Seminar Series on Modern AI DOORS ARE OPEN TO EVERYBODY!!! Past Speakers: Yann LeCun, Yoshua Bengio, Stefano Soatto, Vladimir Vapnik, David Blei, Richard J. Roberts, Anima Anadkumar, Martial Hebert, Tony Jebara Future confirmed speakers: Manuela Veloso, Eric Kandel, Francis Bach, Raia Hadsell, Leon Bottou, Michael Kearns, Nicol`o Cesa-Bianchi