2. Nice to Meet You
antimo.musone@fifthingenium.com
Antimo Musone
Co-founder of FifthIngenium
@AntimoMusone
Slideshare: https://www.slideshare.net/tigermen2001
Linkedin: https://it.linkedin.com/in/antimo-musone
Blog: http://fifthingenium.com/blog
3. Nice to Meet You
matteo.valoriani@fifthingenium.com
Matteo Valoriani, PhD
CEO of FifthIngenium
mvaloriani at gmail.com
@MatteoValoriani
Slideshare: www.slideshare.net/MatteoValoriani
Linkedin: https://it.linkedin.com/in/matteovaloriani
Blog: http://fifthingenium.com/blog
GitHub: https://github.com/mvaloriani
4.
5. Agenda
Computing evolution
Industry (0.)4.0?
Mixed Reality
Maintenance Process
Holographic Maintenance Process
Machine Learning / Advanced Analytics
Predictive Maintenance (cloud)
AI Supported Maintenance (At the Edge)
Conclusion
25. Machine Learning / Advanced Analytics
Vision Analytics
Recommenda-tion
engines
Advertising analysis
Weather forecasting
for business planning
Social network
analysis
Legal
discovery and
document archiving
Pricing analysis
Fraud
detection
Churn
analysis
Equipment
monitoring
Location-based
tracking and services
Personalized
Insurance
Machine learning &
predictive analytics are
core capabilities that are
needed throughout your
business
26. Machine Learning Overview
Formal definition: “The field of machine learning is concerned with the question of
how to construct computer programs that automatically improve with experience” -
Tom M. Mitchell
Another definition: “The goal of machine learning is to program computers to use
example data or past experience to solve a given problem.” – Introduction to Machine Learning, 2nd
Edition, MIT Press
ML often involves two primary techniques:
▪ Supervised Learning: Finding the mapping between inputs and outputs using correct values to “train”
a model;
▪ Unsupervised Learning: Finding patterns in the input data (similar to Density Estimates in Statistics).
27. Machine Learning / Advanced Analytics (ML & AI)
techniques enable multiple use cases
Fraud detection, credit risk/scoring, customer
behaviour (e.g., churn), insurance underwriting
AML transaction monitoring, anomaly detection in
cyber security
Algorithmic trading
Algorithmic trading, unstructured data processing (see
below)
Fraud and market abuse investigation
Sales & marketing, risk analysis, scheduling, resource
allocation
Automation of paper-based processes (e.g., claims
processing, accounts payable, trade finance)
Authentication, insurance claims analysis
Telephone surveillance (insider trading, etc.), voice
sentiment analysis
Email surveillance, Machine Translation, help
systems/chatbots, report writing, contract review
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Deep Learning
Social Network Analytics
Visualisation & Reporting
Optical Character
Recognition
Image
Voice
Natural Language
Processing
Predictive Analytics
Descriptive & Prescriptive
Analytics
Unstructured Data
Processing
Machine Learning &
Advanced Analytics
ExampleusecasesinFinancialServices
28. AI Platform Stack
Linux ( CentOS, Ubuntu, RedHat, SUSEDebian), Android, Windows,
BSD, iOS, MacOS
x86, ARM, CUDA, Mali, Adreno
CUDA, MPI, OpenMP, TBB, OpenCL, StarPU
Languages
AI Platforms
Parallel
programming
Basic libraries
Compilers
Operating
System
Hardware
Microsoft Azure, Google Cloud, Amazon, Watson etc.
Tensorflow, Caffe, Torch, Theano, TensorRT, CNTK, OpenCV
LLVM,GCC, ICC, Rose, PGI, Lift …
cuBLAS, BLAS, MAGMA, ViennaCL, CLBlast, cuDNN, openBLAS, clBLAS, libDNN,
tinyDNN, ARM compute lib etc
C++, Fortran, Java, Python, Byte code, Assembler
29. Microsoft Azure ML Platform
Azure ML a production environment that simplifies the development and deployment of machine learning
models. The platform enables growing community of developers and data scientists to share their analytics
solutions.
Capabilities :
▪ Machine Learining Service
▪ Bot Service
▪ Bing Web Search API
▪ Text Analytics API
▪ Face API
▪ Large scale machine learning service
▪ Computer Vision API
▪ Custom Vision Service