SlideShare ist ein Scribd-Unternehmen logo
1 von 55
Deep Learning: Advances Of The
Last Year
Tyantov Eduard
Convolutional Neural Networks
Neural Networks
1. Multilayer perceptron, 1960 2. Backpropagation algorithm, 1974
3. Convolutional neural
network, 1990s
Convolution
Color image
(RGB)
Feature maps3
channels
Convolutions
Input
output
Pooling
ImageNet Challenge
Network Architecture
VGG-network
Advances in
Computer Vision
#1 OCR: Google Maps & Street View
Results
– State-of-the-art: 84.2% accuracy on French Street Name Signs dataset
– Deployed to recognize street numbers and addresses
– Expanded to detect business store-front signs
#2 Visual reasoning
Results
– CLEVR results included super-human performance at 95.5% (68.5 prev.)
– Potential in B2B: “is store shelf properly merchandised ?”
#3 Pix2Code
Overview
– Generating Code from a Graphical User Interface Screenshot
– Experimental, 77% accuracy
#4 SketchRNN: Teaching Machines to Draw
Overview
• Dataset of vector drawing obtained from “Quick, Draw!”
– an online game (70K examples)
• The model learned how to draw simple concepts
#4 SketchRNN: Examples
Arithmetic on
latent
representation
GAN
#5 What is GAN ?
Overview
– Generative Adversarial Networks – two neural networks contesting with each other
– Primarily applied to modeling natural images
– Architecture
• Generator creates fake pictures and tries to fool Discriminator
• Discriminator distinguishes generated from real
#5 GAN: Architecture
G generates pictures from
numbers (latent representation)
Generated Bedrooms
#6 GAN: latent space
Demo
#7 Face aging with conditional GAN
Overview
– Trained on IMDB dataset (age known)
– One can add parameters to latent space, i.e. age
– During evaluation age component is changed
#8 Generative Adversarial Text to Image Synthesis
Overview
– Generating realistic images from text
– G outputs fake images based on text, D distinguish fake/real image+text
#9 Professional-Level Photographs
Aspects
– Dataset:
• professional photos
• negative examples were generated by applying a combination of image filters, degrading their appearance
– Model: GAN, Generator tries to fix negative examples
– AI travels thousands of panoramas to pick & enhance
#10 Pix2pix
Overview
– Image-to-image translation
– Generator learns to transfer between domains
#11 Pix2pix: cat examples
Demo
#12 CycleGAN: tasks
xxxx
– xxxx
#12 CycleGAN
Overview
– Unpaired Image-to-Image Translation (like Style Transfer)
– 2 pairs of G + D from one domain to another and backward
– Cycle consistency
– More powerful and controllable than Style Transfer (object transfigurations, …)
#12 CycleGAN: failure cases
#13 Molecule development in oncology
Overview
– AAE model learns underlying distribution of molecular fingerprints
– The output was used to screen 72M and select candidates with potential anti-cancer properties
– Result: 69 new molecule (half is already using to fight cancer)
#14 Adversarial attacks
Overview
– Adversarial examples—inputs formed by applying small but intentionally worst-case perturbations
– Would-be problem for future ML systems, now in active research
– Potential usage for us:
• robust defense for Antispam
• adversarial Captcha
#14 Adversarial attacks: examples IRL
impersonations to fool Face Recognition
Perturbations in the shape of the text “LOVE HATE” - self-driving cars
Speech
#15 WaveNet: A Generative Model for Raw Audio
Results
– WaveNets are able to generate speech which mimics any human voice
– Text To Speech: State of the art, reduced the gap with human performance by over 50%
– Can be used to synthesize audio signals such as music
Text Piano
#16 Lips Reading
Results
– Trained on TV dataset
– Model can operate on visual, audio or both
– Beats a professional lip reader from BBC
#17 Obama Lip Sync
Training on a large amount of video of the same person we can create
believable video from audio with convincing lip sync
Text
#18 Google Neural Machine Translation
Overview
– Architecture: RecurrentNN + Attention + a lot of tricks
– GNMT reduces translation errors by 55%-85% on several major language
#19 Negotiations. Deal or no deal ?
How
– Supervised on human dialogues and then finetuned on AI vs AI
– Bot simulates a future conversation to the end and picks highest EV
Results
– There were cases where agents initially feigned interest in a valueless item
– A step toward creating bots than can reason, converse, and negotiate
#19 Negotiations: out of control
Bob: I can i i everything else
Alice: balls have zero to me to me to me to me to me to me to me to me to
Bob: you i everything else
Alice: balls have a ball to me to me to me to me to me to me to me to me
Reinforcement Learning
#20 What is RL ?
Task
• Learn how to behave successfully to achieve a
goal while interacting with external enviroment
• Learn via experience!
Examples
• Game playing
• Traffic control
• Robotics
#21 RL: advance in games
Atari games (2600) – RL surpasses human performance in a majority of games (2015 year)
Results
• Using auxiliary tasks (pixel and reward
prediction) training is 10x faster
• On Atari games – 9x super human performance
• 87% human performance on Labyrinth
#22 Mastering the game of Go
“We showed AlphaGo a large number of strong amateur games to help it develop its own understanding of what
reasonable human play looks like. Then we had it play against different versions of itself thousands of times, each
time learning from its mistakes and incrementally improving until it became immensely strong, through a process
known as reinforcement learning.”
Overview
– Deepmind’s AlphaGo beats all the human champions
– was awarded professional 9-dan
– … and will retire
#23 Dota
Overview
– Bot has learned entirely via self-play
– Beats the top pros at 1v1 during The International 2017
#24 Robots that Learn
One-shot learning
System can learn a behavior from a single demonstration delivered within a simulator, then reproduce that
behavior in different setups in reality.
#25 Locomotion Behaviors in Rich Environments
Overview
– Trained: simulated bodies on a diverse set of challenging terrains and obstacles
– Simple reward function: progress
– Result: rich environments promote complex behavior
#26 Learning from Human Preferences
Overview
– No goal system
– Algorithm can infer what human want by being told what’s of 2 better
900 bits of
human feedback
#26 Learning from Human Preferences: failure case
– Goal: grasp items
– Result: algorithm tricked evaluators (it only appeared to grasp)
#27 Production: Cooling a Data Center
Overview
– Data: historical, collected by thousands of sensors (temperatures, power, pump speeds, setpoints, …)
– Ensemble of deep neural networks
General advances
#28 One Model To Learn Them All
Overview
– One model to learn 8 tasks of multiple domains (image, text, speech)
Results
– Metrics are similar to state-of-the-art on large tasks, better on small
– Transfer learning across domains
#29 Training Imagenet in 1 hour
Overview
– 29 hours on 8 GPU -> 1 hour on 256 GPU cluster
– 90% scaling efficiency (minibatch of 8192)
News
#30 Self-driving cars
Overview
– Google’s Waymo has launched beta-program
• 3 million miles driven
– Intels’s MobilEye & BMW & Audi – fully autonomous cars in 2021
#31 Health
Overview
– Data Science Bowl 2017 fights cancer ($1m in prizes)
– DeepMind focuses on Health problems
• Assisting Pathologists in Detecting Cancer with Deep Learning
A closeup of a lymph node biopsy
Breast
#32 Investments & Teams
Investments
– OpenAI: $1 billion by Musk & Co
– China to become World Leader in AI by 2030, to build domestic industry worth almost $150 billion
Teams
Amount of employees (not precise, universities not included):
– Facebook’s FAIR - 80
– Google’s DeepMind – 250
– GoogleBrain - 30
– OpenAI – 10
– Baidu – 1300
– Microsoft Research AI - 100
Thanks!
Questions?

Weitere ähnliche Inhalte

Was ist angesagt?

Deep Learning in Python with Tensorflow for Finance
Deep Learning in Python with Tensorflow for FinanceDeep Learning in Python with Tensorflow for Finance
Deep Learning in Python with Tensorflow for FinanceBen Ball
 
Introduction to deep learning in python and Matlab
Introduction to deep learning in python and MatlabIntroduction to deep learning in python and Matlab
Introduction to deep learning in python and MatlabImry Kissos
 
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Turi, Inc.
 
Deep learning: what? how? why? How to win a Kaggle competition
Deep learning: what? how? why? How to win a Kaggle competitionDeep learning: what? how? why? How to win a Kaggle competition
Deep learning: what? how? why? How to win a Kaggle competition317070
 
do adversarially robust image net models transfer better
do adversarially robust image net models transfer betterdo adversarially robust image net models transfer better
do adversarially robust image net models transfer betterLEE HOSEONG
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer VisionDavid Dao
 
Using Optimal Learning to Tune Deep Learning Pipelines
Using Optimal Learning to Tune Deep Learning PipelinesUsing Optimal Learning to Tune Deep Learning Pipelines
Using Optimal Learning to Tune Deep Learning PipelinesScott Clark
 
Face recognition v1
Face recognition v1Face recognition v1
Face recognition v1San Kim
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewLEE HOSEONG
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningMehrnaz Faraz
 
Workshop - Introduction to Machine Learning with R
Workshop - Introduction to Machine Learning with RWorkshop - Introduction to Machine Learning with R
Workshop - Introduction to Machine Learning with RShirin Elsinghorst
 
Introduction to deep learning @ Startup.ML by Andres Rodriguez
Introduction to deep learning @ Startup.ML by Andres RodriguezIntroduction to deep learning @ Startup.ML by Andres Rodriguez
Introduction to deep learning @ Startup.ML by Andres RodriguezIntel Nervana
 
Mitchell's Face Recognition
Mitchell's Face RecognitionMitchell's Face Recognition
Mitchell's Face Recognitionbutest
 
Reinforcement Learning for Self Driving Cars
Reinforcement Learning for Self Driving CarsReinforcement Learning for Self Driving Cars
Reinforcement Learning for Self Driving CarsSneha Ravikumar
 
Intel Nervana Artificial Intelligence Meetup 11/30/16
Intel Nervana Artificial Intelligence Meetup 11/30/16Intel Nervana Artificial Intelligence Meetup 11/30/16
Intel Nervana Artificial Intelligence Meetup 11/30/16Intel Nervana
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2Park Chunduck
 
2010 deep learning and unsupervised feature learning
2010 deep learning and unsupervised feature learning2010 deep learning and unsupervised feature learning
2010 deep learning and unsupervised feature learningVan Thanh
 

Was ist angesagt? (20)

Deep Learning in Python with Tensorflow for Finance
Deep Learning in Python with Tensorflow for FinanceDeep Learning in Python with Tensorflow for Finance
Deep Learning in Python with Tensorflow for Finance
 
Introduction to deep learning in python and Matlab
Introduction to deep learning in python and MatlabIntroduction to deep learning in python and Matlab
Introduction to deep learning in python and Matlab
 
Scene understanding
Scene understandingScene understanding
Scene understanding
 
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
 
Deep learning: what? how? why? How to win a Kaggle competition
Deep learning: what? how? why? How to win a Kaggle competitionDeep learning: what? how? why? How to win a Kaggle competition
Deep learning: what? how? why? How to win a Kaggle competition
 
do adversarially robust image net models transfer better
do adversarially robust image net models transfer betterdo adversarially robust image net models transfer better
do adversarially robust image net models transfer better
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
Using Optimal Learning to Tune Deep Learning Pipelines
Using Optimal Learning to Tune Deep Learning PipelinesUsing Optimal Learning to Tune Deep Learning Pipelines
Using Optimal Learning to Tune Deep Learning Pipelines
 
Face recognition v1
Face recognition v1Face recognition v1
Face recognition v1
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 Review
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Workshop - Introduction to Machine Learning with R
Workshop - Introduction to Machine Learning with RWorkshop - Introduction to Machine Learning with R
Workshop - Introduction to Machine Learning with R
 
C3 w2
C3 w2C3 w2
C3 w2
 
Introduction to deep learning @ Startup.ML by Andres Rodriguez
Introduction to deep learning @ Startup.ML by Andres RodriguezIntroduction to deep learning @ Startup.ML by Andres Rodriguez
Introduction to deep learning @ Startup.ML by Andres Rodriguez
 
Mitchell's Face Recognition
Mitchell's Face RecognitionMitchell's Face Recognition
Mitchell's Face Recognition
 
Reinforcement Learning for Self Driving Cars
Reinforcement Learning for Self Driving CarsReinforcement Learning for Self Driving Cars
Reinforcement Learning for Self Driving Cars
 
Deep learning - a primer
Deep learning - a primerDeep learning - a primer
Deep learning - a primer
 
Intel Nervana Artificial Intelligence Meetup 11/30/16
Intel Nervana Artificial Intelligence Meetup 11/30/16Intel Nervana Artificial Intelligence Meetup 11/30/16
Intel Nervana Artificial Intelligence Meetup 11/30/16
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2
 
2010 deep learning and unsupervised feature learning
2010 deep learning and unsupervised feature learning2010 deep learning and unsupervised feature learning
2010 deep learning and unsupervised feature learning
 

Ähnlich wie Deep Learning: Advances Of The Last Year

Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Codemotion
 
Ordina Accelerator program 2019 - DevOps CI-CD
Ordina Accelerator program 2019 - DevOps CI-CDOrdina Accelerator program 2019 - DevOps CI-CD
Ordina Accelerator program 2019 - DevOps CI-CDBert Koorengevel
 
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유NAVER Engineering
 
230208 MLOps Getting from Good to Great.pptx
230208 MLOps Getting from Good to Great.pptx230208 MLOps Getting from Good to Great.pptx
230208 MLOps Getting from Good to Great.pptxArthur240715
 
Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?
Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?
Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?Digipolis Antwerpen
 
Fast Parallel Similarity Calculations with FPGA Hardware
Fast Parallel Similarity Calculations with FPGA HardwareFast Parallel Similarity Calculations with FPGA Hardware
Fast Parallel Similarity Calculations with FPGA HardwareTigerGraph
 
Semi-Supervised Insight Generation from Petabyte Scale Text Data
Semi-Supervised Insight Generation from Petabyte Scale Text DataSemi-Supervised Insight Generation from Petabyte Scale Text Data
Semi-Supervised Insight Generation from Petabyte Scale Text DataTech Triveni
 
Machine_Learning_with_MATLAB_Seminar_Latest.pdf
Machine_Learning_with_MATLAB_Seminar_Latest.pdfMachine_Learning_with_MATLAB_Seminar_Latest.pdf
Machine_Learning_with_MATLAB_Seminar_Latest.pdfCarlos Paredes
 
Enabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesEnabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesWithTheBest
 
Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Turi, Inc.
 
AI INTRODUCTION.pptx,INFORMATION TECHNOLOGY
AI INTRODUCTION.pptx,INFORMATION TECHNOLOGYAI INTRODUCTION.pptx,INFORMATION TECHNOLOGY
AI INTRODUCTION.pptx,INFORMATION TECHNOLOGYsantoshverma90
 
Color based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlabColor based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlabKamal Pradhan
 
Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...
Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...
Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...polochau
 
Lessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixLessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixJustin Basilico
 
Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...
Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...
Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...Dan Cundiff
 
Webinar: Machine Learning para Microcontroladores
Webinar: Machine Learning para MicrocontroladoresWebinar: Machine Learning para Microcontroladores
Webinar: Machine Learning para MicrocontroladoresEmbarcados
 
Generative AI at the edge.pdf
Generative AI at the edge.pdfGenerative AI at the edge.pdf
Generative AI at the edge.pdfQualcomm Research
 
Siddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobileSiddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobileLviv Startup Club
 

Ähnlich wie Deep Learning: Advances Of The Last Year (20)

Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
 
Ordina Accelerator program 2019 - DevOps CI-CD
Ordina Accelerator program 2019 - DevOps CI-CDOrdina Accelerator program 2019 - DevOps CI-CD
Ordina Accelerator program 2019 - DevOps CI-CD
 
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
Beyond TensorBoard: AutoML을 위한 interactive visual analytics 서비스 개발 경험 공유
 
230208 MLOps Getting from Good to Great.pptx
230208 MLOps Getting from Good to Great.pptx230208 MLOps Getting from Good to Great.pptx
230208 MLOps Getting from Good to Great.pptx
 
Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?
Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?
Meetup 21/9/2017 - Image Recogonition: onmisbaar voor een slimme stad?
 
Fast Parallel Similarity Calculations with FPGA Hardware
Fast Parallel Similarity Calculations with FPGA HardwareFast Parallel Similarity Calculations with FPGA Hardware
Fast Parallel Similarity Calculations with FPGA Hardware
 
Semi-Supervised Insight Generation from Petabyte Scale Text Data
Semi-Supervised Insight Generation from Petabyte Scale Text DataSemi-Supervised Insight Generation from Petabyte Scale Text Data
Semi-Supervised Insight Generation from Petabyte Scale Text Data
 
Machine_Learning_with_MATLAB_Seminar_Latest.pdf
Machine_Learning_with_MATLAB_Seminar_Latest.pdfMachine_Learning_with_MATLAB_Seminar_Latest.pdf
Machine_Learning_with_MATLAB_Seminar_Latest.pdf
 
Enabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesEnabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. Lowndes
 
Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015
 
AI INTRODUCTION.pptx,INFORMATION TECHNOLOGY
AI INTRODUCTION.pptx,INFORMATION TECHNOLOGYAI INTRODUCTION.pptx,INFORMATION TECHNOLOGY
AI INTRODUCTION.pptx,INFORMATION TECHNOLOGY
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Color based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlabColor based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlab
 
Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...
Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...
Human-Centered AI: Scalable, Interactive Tools for Interpretation and Attribu...
 
Lessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixLessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at Netflix
 
Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...
Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...
Splunk All the Things: Our First 3 Months Monitoring Web Service APIs - Splun...
 
Webinar: Machine Learning para Microcontroladores
Webinar: Machine Learning para MicrocontroladoresWebinar: Machine Learning para Microcontroladores
Webinar: Machine Learning para Microcontroladores
 
Null
NullNull
Null
 
Generative AI at the edge.pdf
Generative AI at the edge.pdfGenerative AI at the edge.pdf
Generative AI at the edge.pdf
 
Siddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobileSiddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobile
 

Mehr von Eduard Tyantov

Эксплуатация ML в Почте Mail.ru
Эксплуатация ML в Почте Mail.ruЭксплуатация ML в Почте Mail.ru
Эксплуатация ML в Почте Mail.ruEduard Tyantov
 
Опыт моделеварения от команды ComputerVision Mail.ru
Опыт моделеварения от команды ComputerVision Mail.ruОпыт моделеварения от команды ComputerVision Mail.ru
Опыт моделеварения от команды ComputerVision Mail.ruEduard Tyantov
 
Саморазвитие: как я не усидел на двух стульях и нашел третий
Саморазвитие: как я не усидел на двух стульях и нашел третийСаморазвитие: как я не усидел на двух стульях и нашел третий
Саморазвитие: как я не усидел на двух стульях и нашел третийEduard Tyantov
 
Project Management 2.0: AI Transformation
Project Management 2.0: AI TransformationProject Management 2.0: AI Transformation
Project Management 2.0: AI TransformationEduard Tyantov
 
Kaggle Google Landmark recognition
Kaggle Google Landmark recognitionKaggle Google Landmark recognition
Kaggle Google Landmark recognitionEduard Tyantov
 
Artisto App, Highload 2016
Artisto App, Highload 2016Artisto App, Highload 2016
Artisto App, Highload 2016Eduard Tyantov
 

Mehr von Eduard Tyantov (6)

Эксплуатация ML в Почте Mail.ru
Эксплуатация ML в Почте Mail.ruЭксплуатация ML в Почте Mail.ru
Эксплуатация ML в Почте Mail.ru
 
Опыт моделеварения от команды ComputerVision Mail.ru
Опыт моделеварения от команды ComputerVision Mail.ruОпыт моделеварения от команды ComputerVision Mail.ru
Опыт моделеварения от команды ComputerVision Mail.ru
 
Саморазвитие: как я не усидел на двух стульях и нашел третий
Саморазвитие: как я не усидел на двух стульях и нашел третийСаморазвитие: как я не усидел на двух стульях и нашел третий
Саморазвитие: как я не усидел на двух стульях и нашел третий
 
Project Management 2.0: AI Transformation
Project Management 2.0: AI TransformationProject Management 2.0: AI Transformation
Project Management 2.0: AI Transformation
 
Kaggle Google Landmark recognition
Kaggle Google Landmark recognitionKaggle Google Landmark recognition
Kaggle Google Landmark recognition
 
Artisto App, Highload 2016
Artisto App, Highload 2016Artisto App, Highload 2016
Artisto App, Highload 2016
 

Kürzlich hochgeladen

Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Delhi Call girls
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...shivangimorya083
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxolyaivanovalion
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfadriantubila
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Researchmichael115558
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
 

Kürzlich hochgeladen (20)

Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 

Deep Learning: Advances Of The Last Year

  • 1. Deep Learning: Advances Of The Last Year Tyantov Eduard
  • 3. Neural Networks 1. Multilayer perceptron, 1960 2. Backpropagation algorithm, 1974 3. Convolutional neural network, 1990s
  • 6.
  • 10. #1 OCR: Google Maps & Street View Results – State-of-the-art: 84.2% accuracy on French Street Name Signs dataset – Deployed to recognize street numbers and addresses – Expanded to detect business store-front signs
  • 11. #2 Visual reasoning Results – CLEVR results included super-human performance at 95.5% (68.5 prev.) – Potential in B2B: “is store shelf properly merchandised ?”
  • 12. #3 Pix2Code Overview – Generating Code from a Graphical User Interface Screenshot – Experimental, 77% accuracy
  • 13. #4 SketchRNN: Teaching Machines to Draw Overview • Dataset of vector drawing obtained from “Quick, Draw!” – an online game (70K examples) • The model learned how to draw simple concepts
  • 14. #4 SketchRNN: Examples Arithmetic on latent representation
  • 15. GAN
  • 16. #5 What is GAN ? Overview – Generative Adversarial Networks – two neural networks contesting with each other – Primarily applied to modeling natural images – Architecture • Generator creates fake pictures and tries to fool Discriminator • Discriminator distinguishes generated from real
  • 17. #5 GAN: Architecture G generates pictures from numbers (latent representation) Generated Bedrooms
  • 18. #6 GAN: latent space Demo
  • 19. #7 Face aging with conditional GAN Overview – Trained on IMDB dataset (age known) – One can add parameters to latent space, i.e. age – During evaluation age component is changed
  • 20. #8 Generative Adversarial Text to Image Synthesis Overview – Generating realistic images from text – G outputs fake images based on text, D distinguish fake/real image+text
  • 21. #9 Professional-Level Photographs Aspects – Dataset: • professional photos • negative examples were generated by applying a combination of image filters, degrading their appearance – Model: GAN, Generator tries to fix negative examples – AI travels thousands of panoramas to pick & enhance
  • 22. #10 Pix2pix Overview – Image-to-image translation – Generator learns to transfer between domains
  • 23. #11 Pix2pix: cat examples Demo
  • 25. #12 CycleGAN Overview – Unpaired Image-to-Image Translation (like Style Transfer) – 2 pairs of G + D from one domain to another and backward – Cycle consistency – More powerful and controllable than Style Transfer (object transfigurations, …)
  • 27. #13 Molecule development in oncology Overview – AAE model learns underlying distribution of molecular fingerprints – The output was used to screen 72M and select candidates with potential anti-cancer properties – Result: 69 new molecule (half is already using to fight cancer)
  • 28. #14 Adversarial attacks Overview – Adversarial examples—inputs formed by applying small but intentionally worst-case perturbations – Would-be problem for future ML systems, now in active research – Potential usage for us: • robust defense for Antispam • adversarial Captcha
  • 29. #14 Adversarial attacks: examples IRL impersonations to fool Face Recognition Perturbations in the shape of the text “LOVE HATE” - self-driving cars
  • 31. #15 WaveNet: A Generative Model for Raw Audio Results – WaveNets are able to generate speech which mimics any human voice – Text To Speech: State of the art, reduced the gap with human performance by over 50% – Can be used to synthesize audio signals such as music Text Piano
  • 32. #16 Lips Reading Results – Trained on TV dataset – Model can operate on visual, audio or both – Beats a professional lip reader from BBC
  • 33. #17 Obama Lip Sync Training on a large amount of video of the same person we can create believable video from audio with convincing lip sync
  • 34. Text
  • 35. #18 Google Neural Machine Translation Overview – Architecture: RecurrentNN + Attention + a lot of tricks – GNMT reduces translation errors by 55%-85% on several major language
  • 36. #19 Negotiations. Deal or no deal ? How – Supervised on human dialogues and then finetuned on AI vs AI – Bot simulates a future conversation to the end and picks highest EV Results – There were cases where agents initially feigned interest in a valueless item – A step toward creating bots than can reason, converse, and negotiate
  • 37. #19 Negotiations: out of control Bob: I can i i everything else Alice: balls have zero to me to me to me to me to me to me to me to me to Bob: you i everything else Alice: balls have a ball to me to me to me to me to me to me to me to me
  • 39. #20 What is RL ? Task • Learn how to behave successfully to achieve a goal while interacting with external enviroment • Learn via experience! Examples • Game playing • Traffic control • Robotics
  • 40. #21 RL: advance in games Atari games (2600) – RL surpasses human performance in a majority of games (2015 year) Results • Using auxiliary tasks (pixel and reward prediction) training is 10x faster • On Atari games – 9x super human performance • 87% human performance on Labyrinth
  • 41. #22 Mastering the game of Go “We showed AlphaGo a large number of strong amateur games to help it develop its own understanding of what reasonable human play looks like. Then we had it play against different versions of itself thousands of times, each time learning from its mistakes and incrementally improving until it became immensely strong, through a process known as reinforcement learning.” Overview – Deepmind’s AlphaGo beats all the human champions – was awarded professional 9-dan – … and will retire
  • 42. #23 Dota Overview – Bot has learned entirely via self-play – Beats the top pros at 1v1 during The International 2017
  • 43. #24 Robots that Learn One-shot learning System can learn a behavior from a single demonstration delivered within a simulator, then reproduce that behavior in different setups in reality.
  • 44. #25 Locomotion Behaviors in Rich Environments Overview – Trained: simulated bodies on a diverse set of challenging terrains and obstacles – Simple reward function: progress – Result: rich environments promote complex behavior
  • 45. #26 Learning from Human Preferences Overview – No goal system – Algorithm can infer what human want by being told what’s of 2 better 900 bits of human feedback
  • 46. #26 Learning from Human Preferences: failure case – Goal: grasp items – Result: algorithm tricked evaluators (it only appeared to grasp)
  • 47. #27 Production: Cooling a Data Center Overview – Data: historical, collected by thousands of sensors (temperatures, power, pump speeds, setpoints, …) – Ensemble of deep neural networks
  • 49. #28 One Model To Learn Them All Overview – One model to learn 8 tasks of multiple domains (image, text, speech) Results – Metrics are similar to state-of-the-art on large tasks, better on small – Transfer learning across domains
  • 50. #29 Training Imagenet in 1 hour Overview – 29 hours on 8 GPU -> 1 hour on 256 GPU cluster – 90% scaling efficiency (minibatch of 8192)
  • 51. News
  • 52. #30 Self-driving cars Overview – Google’s Waymo has launched beta-program • 3 million miles driven – Intels’s MobilEye & BMW & Audi – fully autonomous cars in 2021
  • 53. #31 Health Overview – Data Science Bowl 2017 fights cancer ($1m in prizes) – DeepMind focuses on Health problems • Assisting Pathologists in Detecting Cancer with Deep Learning A closeup of a lymph node biopsy Breast
  • 54. #32 Investments & Teams Investments – OpenAI: $1 billion by Musk & Co – China to become World Leader in AI by 2030, to build domestic industry worth almost $150 billion Teams Amount of employees (not precise, universities not included): – Facebook’s FAIR - 80 – Google’s DeepMind – 250 – GoogleBrain - 30 – OpenAI – 10 – Baidu – 1300 – Microsoft Research AI - 100