SlideShare a Scribd company logo
Cyril Banino-Rokkones
Telenor Research
2
I know nothing about Deep Learning
3
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
4
AI was the weak link until Deep Learning
matured
5
China's Search Giant Goes Deep
AI was the weak link until Deep Learning
matured
6
http://www.iro.umontreal.ca/~bengioy/dlbook/intro.html
Loose inspiration from the brain
7
China's Search Giant Goes Deep
Large Neural Nets perform better than small ones
8
China's Search Giant Goes Deep
Google Brain project – 1 billion connections – 1
week of youtube watching.
9 China's Search Giant Goes Deep
From 16k CPUs to 3 GPUs
From 1M connections to 10 B
10
China's Search Giant Goes Deep
Applications of Deep Learning
11
China's Search Giant Goes Deep
Voice interface to assist computer-illiterates
12
China's Search Giant Goes Deep
Image-search for impossible queries
13
China's Search Giant Goes Deep
Image-search for impossible queries
14
China's Search Giant Goes Deep
Image-queries to find stuff impossible to describe
15
China's Search Giant Goes Deep
16
“Whoever wins AI wins the Internet.” A. Ng.
Google, Facebook and other tech companies race to develop artificial intelligence
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
17
Perceptrons makes decisions by weighing evidence
18 http://neuralnetworksanddeeplearning.com/chap1.html
Example: NAND gate
19 http://neuralnetworksanddeeplearning.com/chap1.html
Wiring several perceptrons for more abstract and complex
decisions
20 http://neuralnetworksanddeeplearning.com/chap1.html
A simple network to classify handwritten digits (MNIST)
21 http://neuralnetworksanddeeplearning.com/chap1.html
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
22
Training Neural Networks: Gradient descent
23
Learning to solve a problem
24 http://neuralnetworksanddeeplearning.com/chap1.html
Forward and Backward passes
25
http://caffe.berkeleyvision.org/tutorial/forward_backward.html
The Unstable Gradient Problem
26
Why it is difficult to train an RNN
Why are deep neural networks hard to train?
Practical advices when training neural networks
(by Ilya Sutskever)
27
• Get good data
• Preprocessing
• Minibatches
• Gradient normalization
• Learning rate schedule
• Learning rate
• Weight Initialization
• Data augmentation
• Dropout
• Ensembling
A Brief Overview of Deep Learning
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
28
Convolutional Neural Network have been here for a while
29
Convolutions
30 Understanding Convolutions
Convolutional Neural Network
31
Conv Nets: A Modular Perspective
Convolutional Neural Network
32
Human-level control through deep reinforcement learning
Intriguing properties of Conv Nets
33
Intriguing properties of neural networks
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
34
Stacked Autoencoders
35
Reducing the Dimensionality of Data with Neural Networks
Stacked Autoencoders
36
Reducing the Dimensionality of Data with Neural Networks
Stacked Autoencoders – semantic Hashing
37
Semantic Hashing
Reducing the Dimensionality of Data with Neural Networks
Behavioral micro-segmentation (training set)
38
1008
275
275
1008
8
150
150
0.011|0.98|0.2| … 0
Bit code
1 0 …~
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
39
40
Word embeddings
Deep Learning, NLP, and Representations
41
Word embeddings and Shared representations
Deep Learning, NLP, and Representations Deep Visual-Semantic Alignments for Generating Image
Descriptions
42
Word embeddings and Recurrent Neural Nets
Deep Learning, NLP, and Representations
43
Word embeddings and Reversible Sentence Representation
Deep Learning, NLP, and Representations
Rich Rashid in Tianjin, October, 25, 2012
Telenor Norway Network topology
Word embeddings applied to Network operations
Use cases:
• Predict failures of Network components.
• Predict congestion levels on Network links.
• Detect mal-functioning devices.
Outline
• Intro to DL (A. Ng)
• Intro to Neural Nets
• Training NN
• Conv Nets
• Autoencoders
• Word Embeddings
• DL@TRD
• Bonus
45
DL@TRD - Motivations
Personal observations:
– DL is hot (hyped?)
– DL supremacy seems ineluctable
– DL can solve a whole bunch of problems
– DL is frontier technology (difficult)
– Little DL competence @ Telenor Research
Personal implications:
– Career development
– Network with partners to get momentum
– Great if this happens in Trondheim
46
DL@TRD - Vision
Establish a strong DL competence center in Trondheim
– A place where
• competence is gathered
• experiences are exchanged
• collaborations are fostered
– Benefits
• Share passion with others near you
• Get momentum for your work
• Funding (SFI, EU money)
– Ideally
• Collaborate across companies on problems
• Common publications
47
Next workshop: 27th March
DL@Telenor – Topics of Interest
NLP tasks
– Speech-to-Text
– Text-to-Speech
– Automatic summarization
– Sentiment analysis
Computer Vision
– Face detection
– Image recognition/classification
 Telenor Applications
– New Digital Services
– Managing our Networks
– Understanding our Customers
48
Stuff we could discuss at DL@TRD
• Training Recurrent Neural Networks
• Long Short Term Memory Networks
• Echo State Networks
• Neural Turing Machines
• Hopfield Nets
• Restricted Bolzman Machines
• Deep beliefs Networks
• Teacher – Student Nets
• Momentum
• Dropout
• Full Bayesian learning
• Hessian free optimization
• Stuff I don´t know I don´t know
49
Conclusion & Forecast
50
• DL techniques can be applied to all sorts of data:
– Could you apply some of these techniques to your data?
• DL models are better than humans at some tasks if fed with enough
data & trained properly
• Within 5-10 years, “information work” tasks will be augmented or even
fully automated
– See Peter Norvig´s talk at InfoQ: Machine Learning for Programming
– Models can take decisions based on millions of records while removing human
biases
 Big data + Deep Learning = unemployment
– New policies and economic measures will be needed to manage the adverse
effects of job computerization
– Schooling will need reforms: routine tasks  non-routine tasks
Thank you
51
btw we´re hiring…

More Related Content

Similar to Deep Learning Big Data Meetup @ Trondheim

Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
Madhu Sanjeevi (Mady)
 
machine learning and neural technology
machine learning and neural technologymachine learning and neural technology
machine learning and neural technology
VarnikaSood
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Amr Rashed
 
AI Deep Learning - CF Machine Learning
AI Deep Learning - CF Machine LearningAI Deep Learning - CF Machine Learning
AI Deep Learning - CF Machine Learning
Karl Seiler
 
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Impetus Technologies
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
Roelof Pieters
 
design and implementation of waste slide share dvgh PPRt.pptx
design and implementation of waste slide share dvgh PPRt.pptxdesign and implementation of waste slide share dvgh PPRt.pptx
design and implementation of waste slide share dvgh PPRt.pptx
luckyj6
 
Performance support
Performance supportPerformance support
Performance support
Darren Nerland
 
Biological Foundations for Deep Learning: Towards Decision Networks
 Biological Foundations for Deep Learning: Towards Decision Networks Biological Foundations for Deep Learning: Towards Decision Networks
Biological Foundations for Deep Learning: Towards Decision Networks
diannepatricia
 
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
Karthik Murugesan
 
Deep learning: the future of recommendations
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendations
Balázs Hidasi
 
Introduction to Deep Learning Technique.pptx
Introduction to Deep Learning Technique.pptxIntroduction to Deep Learning Technique.pptx
Introduction to Deep Learning Technique.pptx
KerenEvangelineI
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Abhishek Bhandwaldar
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
Charmi Chokshi
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
doppenhe
 
AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...
AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...
AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...
AILABS Academy
 
lec01.pptx
lec01.pptxlec01.pptx
lec01.pptx
Basavaraju43
 
AI Technology Overview and Career Advice
AI Technology Overview and Career AdviceAI Technology Overview and Career Advice
AI Technology Overview and Career Advice
Kunling Geng
 
Machine Learning for Data Extraction
Machine Learning for Data ExtractionMachine Learning for Data Extraction
Machine Learning for Data Extraction
Dasha Herrmannova
 
Big Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningBig Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep Learning
Poo Kuan Hoong
 

Similar to Deep Learning Big Data Meetup @ Trondheim (20)

Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
 
machine learning and neural technology
machine learning and neural technologymachine learning and neural technology
machine learning and neural technology
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
AI Deep Learning - CF Machine Learning
AI Deep Learning - CF Machine LearningAI Deep Learning - CF Machine Learning
AI Deep Learning - CF Machine Learning
 
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
 
design and implementation of waste slide share dvgh PPRt.pptx
design and implementation of waste slide share dvgh PPRt.pptxdesign and implementation of waste slide share dvgh PPRt.pptx
design and implementation of waste slide share dvgh PPRt.pptx
 
Performance support
Performance supportPerformance support
Performance support
 
Biological Foundations for Deep Learning: Towards Decision Networks
 Biological Foundations for Deep Learning: Towards Decision Networks Biological Foundations for Deep Learning: Towards Decision Networks
Biological Foundations for Deep Learning: Towards Decision Networks
 
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
BIng NLP Expert - Dl summer-school-2017.-jianfeng-gao.v2
 
Deep learning: the future of recommendations
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendations
 
Introduction to Deep Learning Technique.pptx
Introduction to Deep Learning Technique.pptxIntroduction to Deep Learning Technique.pptx
Introduction to Deep Learning Technique.pptx
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...
AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...
AILABS - Lecture Series - Is AI the New Electricity? - Advances In Machine Le...
 
lec01.pptx
lec01.pptxlec01.pptx
lec01.pptx
 
AI Technology Overview and Career Advice
AI Technology Overview and Career AdviceAI Technology Overview and Career Advice
AI Technology Overview and Career Advice
 
Machine Learning for Data Extraction
Machine Learning for Data ExtractionMachine Learning for Data Extraction
Machine Learning for Data Extraction
 
Big Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep LearningBig Data Malaysia - A Primer on Deep Learning
Big Data Malaysia - A Primer on Deep Learning
 

Recently uploaded

National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
Quotidiano Piemontese
 
Generative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to ProductionGenerative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to Production
Aggregage
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
Neo4j
 
Full-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalizationFull-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalization
Zilliz
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
sonjaschweigert1
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
Kumud Singh
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
DianaGray10
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
Large Language Model (LLM) and it’s Geospatial Applications
Large Language Model (LLM) and it’s Geospatial ApplicationsLarge Language Model (LLM) and it’s Geospatial Applications
Large Language Model (LLM) and it’s Geospatial Applications
Rohit Gautam
 
Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...
Zilliz
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
Alex Pruden
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
Matthew Sinclair
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
名前 です男
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
SOFTTECHHUB
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
DianaGray10
 

Recently uploaded (20)

National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
 
Generative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to ProductionGenerative AI Deep Dive: Advancing from Proof of Concept to Production
Generative AI Deep Dive: Advancing from Proof of Concept to Production
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
 
Full-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalizationFull-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalization
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
Large Language Model (LLM) and it’s Geospatial Applications
Large Language Model (LLM) and it’s Geospatial ApplicationsLarge Language Model (LLM) and it’s Geospatial Applications
Large Language Model (LLM) and it’s Geospatial Applications
 
Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
 

Deep Learning Big Data Meetup @ Trondheim

  • 2. 2
  • 3. I know nothing about Deep Learning 3
  • 4. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 4
  • 5. AI was the weak link until Deep Learning matured 5 China's Search Giant Goes Deep
  • 6. AI was the weak link until Deep Learning matured 6 http://www.iro.umontreal.ca/~bengioy/dlbook/intro.html
  • 7. Loose inspiration from the brain 7 China's Search Giant Goes Deep
  • 8. Large Neural Nets perform better than small ones 8 China's Search Giant Goes Deep
  • 9. Google Brain project – 1 billion connections – 1 week of youtube watching. 9 China's Search Giant Goes Deep
  • 10. From 16k CPUs to 3 GPUs From 1M connections to 10 B 10 China's Search Giant Goes Deep
  • 11. Applications of Deep Learning 11 China's Search Giant Goes Deep
  • 12. Voice interface to assist computer-illiterates 12 China's Search Giant Goes Deep
  • 13. Image-search for impossible queries 13 China's Search Giant Goes Deep
  • 14. Image-search for impossible queries 14 China's Search Giant Goes Deep
  • 15. Image-queries to find stuff impossible to describe 15 China's Search Giant Goes Deep
  • 16. 16 “Whoever wins AI wins the Internet.” A. Ng. Google, Facebook and other tech companies race to develop artificial intelligence
  • 17. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 17
  • 18. Perceptrons makes decisions by weighing evidence 18 http://neuralnetworksanddeeplearning.com/chap1.html
  • 19. Example: NAND gate 19 http://neuralnetworksanddeeplearning.com/chap1.html
  • 20. Wiring several perceptrons for more abstract and complex decisions 20 http://neuralnetworksanddeeplearning.com/chap1.html
  • 21. A simple network to classify handwritten digits (MNIST) 21 http://neuralnetworksanddeeplearning.com/chap1.html
  • 22. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 22
  • 23. Training Neural Networks: Gradient descent 23
  • 24. Learning to solve a problem 24 http://neuralnetworksanddeeplearning.com/chap1.html
  • 25. Forward and Backward passes 25 http://caffe.berkeleyvision.org/tutorial/forward_backward.html
  • 26. The Unstable Gradient Problem 26 Why it is difficult to train an RNN Why are deep neural networks hard to train?
  • 27. Practical advices when training neural networks (by Ilya Sutskever) 27 • Get good data • Preprocessing • Minibatches • Gradient normalization • Learning rate schedule • Learning rate • Weight Initialization • Data augmentation • Dropout • Ensembling A Brief Overview of Deep Learning
  • 28. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 28
  • 29. Convolutional Neural Network have been here for a while 29
  • 31. Convolutional Neural Network 31 Conv Nets: A Modular Perspective
  • 32. Convolutional Neural Network 32 Human-level control through deep reinforcement learning
  • 33. Intriguing properties of Conv Nets 33 Intriguing properties of neural networks
  • 34. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 34
  • 35. Stacked Autoencoders 35 Reducing the Dimensionality of Data with Neural Networks
  • 36. Stacked Autoencoders 36 Reducing the Dimensionality of Data with Neural Networks
  • 37. Stacked Autoencoders – semantic Hashing 37 Semantic Hashing Reducing the Dimensionality of Data with Neural Networks
  • 38. Behavioral micro-segmentation (training set) 38 1008 275 275 1008 8 150 150 0.011|0.98|0.2| … 0 Bit code 1 0 …~
  • 39. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 39
  • 40. 40 Word embeddings Deep Learning, NLP, and Representations
  • 41. 41 Word embeddings and Shared representations Deep Learning, NLP, and Representations Deep Visual-Semantic Alignments for Generating Image Descriptions
  • 42. 42 Word embeddings and Recurrent Neural Nets Deep Learning, NLP, and Representations
  • 43. 43 Word embeddings and Reversible Sentence Representation Deep Learning, NLP, and Representations Rich Rashid in Tianjin, October, 25, 2012
  • 44. Telenor Norway Network topology Word embeddings applied to Network operations Use cases: • Predict failures of Network components. • Predict congestion levels on Network links. • Detect mal-functioning devices.
  • 45. Outline • Intro to DL (A. Ng) • Intro to Neural Nets • Training NN • Conv Nets • Autoencoders • Word Embeddings • DL@TRD • Bonus 45
  • 46. DL@TRD - Motivations Personal observations: – DL is hot (hyped?) – DL supremacy seems ineluctable – DL can solve a whole bunch of problems – DL is frontier technology (difficult) – Little DL competence @ Telenor Research Personal implications: – Career development – Network with partners to get momentum – Great if this happens in Trondheim 46
  • 47. DL@TRD - Vision Establish a strong DL competence center in Trondheim – A place where • competence is gathered • experiences are exchanged • collaborations are fostered – Benefits • Share passion with others near you • Get momentum for your work • Funding (SFI, EU money) – Ideally • Collaborate across companies on problems • Common publications 47 Next workshop: 27th March
  • 48. DL@Telenor – Topics of Interest NLP tasks – Speech-to-Text – Text-to-Speech – Automatic summarization – Sentiment analysis Computer Vision – Face detection – Image recognition/classification  Telenor Applications – New Digital Services – Managing our Networks – Understanding our Customers 48
  • 49. Stuff we could discuss at DL@TRD • Training Recurrent Neural Networks • Long Short Term Memory Networks • Echo State Networks • Neural Turing Machines • Hopfield Nets • Restricted Bolzman Machines • Deep beliefs Networks • Teacher – Student Nets • Momentum • Dropout • Full Bayesian learning • Hessian free optimization • Stuff I don´t know I don´t know 49
  • 50. Conclusion & Forecast 50 • DL techniques can be applied to all sorts of data: – Could you apply some of these techniques to your data? • DL models are better than humans at some tasks if fed with enough data & trained properly • Within 5-10 years, “information work” tasks will be augmented or even fully automated – See Peter Norvig´s talk at InfoQ: Machine Learning for Programming – Models can take decisions based on millions of records while removing human biases  Big data + Deep Learning = unemployment – New policies and economic measures will be needed to manage the adverse effects of job computerization – Schooling will need reforms: routine tasks  non-routine tasks