SlideShare a Scribd company logo

孫民/從電腦視覺看人工智慧 : 下一件大事

•
•
台灣資料科學年會
台灣資料科學年會

孫民博士目前任教於國立清華大學電機系，他畢業於國立交通大學電子工程學系後，取得史坦福電機碩士、密西根安雅堡電機系統組博士、以及西雅圖華盛頓大學計算機工程博士後的經歷。他的研究興趣在電腦視覺、機器學習、以及人機互動領域，近年來基於深度學習在電腦視覺的突破，他致力於開發橫跨人工智慧不同子領域的系統，如自動影片文字描述 ( 視覺 x 自然語言 )、以及與人類行為互動的智慧機器 ( 視覺 x 控制 )。

Data & Analytics
1 of 56
Download to read offline
Ar#ficial  Intelligence:     The  Next  Big  Thing     from  a  computer  vision  perspec0ve     VSLab   清大電機 孫民
What’s  the  Next  Big  Thing?   h2p://research.microso6.com/en-­‐us/um/redmond/events/fs2015  
Goal     “big  data  being  the  source,  machine   learning  being  the  technique,  and  AI   being  the  outcome”     by  Prof.  Hsuan-­‐Tien  Lin  at  IEEE  BigData  2016     Many  kinds  of  source  (data)  and   outcomes  (AI  tasks)  can  be  trained  end-­‐ to-­‐end  using  Deep  Learning  (DL)  
Classical  AI  Tests:  Turing  Test   by  Alan  Turing  in  1950  
Chatbot@F8   h2ps://developers.facebook.com/videos/f8-­‐2016/keynote/  
Classical  AI  Tests:  CAPTCHA  
Breaking  CAPTCHA   by  vicarious.com  
AlphaGo   2016  by  Google  DeepMind   Are  these  what  AI  all  about?  
2014  Subfields  of  AI  
2015   Ar#fical  General  Intelligence  (AGI)  
Deep  Learning  (DL)   •  Data   •  GPU  Compu0ng   •  Talents  
DL  Fuses  AI-­‐subfields   •  Vision  and  Language     •  Vision  and  Control   h2p://mscoco.org/   Atari  Breakout  game  &  AlphaGo,  DeepMind.   -­‐>  AGI   •  Mul0ple  Encoding  and  Decoding  
Image  Cap#oning   f(                      )  =   The  man  at  bat  is   ready  to  swing     at  the  pitch   Vision   Language   Recurrent  Neuron  Network  (RNN)   credit:  Nature   convolu0ons   Convolu#on  Neuron  Network  (CNN)   credit:  wiki  
Image  Ques#on  Answering   h2p://visualqa.org/  
Zhen  et  al.  ECCV  2016  from  VSLab  and  Stanford  AI  Lab  
Big  Video  Data  with  Titles   •  Pairs  of   Raw  Video     CNN   CNN   CNN   CNN   Title  
Viral  Videos   Google  for  “viral  video  company”  
Large  Video  Repository   Currently  28740  videos  and  keep  growing  
DL  Fuses  AI-­‐subfields   •  Vision  and  Language     •  Vision  and  Control   h2p://mscoco.org/   Atari  Breakout  game  &  AlphaGo,  DeepMind.   -­‐>  AGI   •  Mul0ple  Encoding  and  Decoding  
Vision  and  Control   h2ps://gym.openai.com/   •  Learning  to  play  game  with  weak  supervision:    Reinforcement  Learning  (RL)  
Where  It  All  Begins  …     by  DeepMind  in  NIPS  2013  Deep  Learning  Wrokshop   Playing Atari with Deep Reinforcement Learning slides  by     Yen-­‐Chen  Lin  
Control:  Learning  to  Act   Play  Breakout  equals  to   •  Input:  screen  images   •  Output:  ac0ons          (do  nothing  |  left  |  right)     Supervised   Classifica0on   slides  by     Yen-­‐Chen  Lin  
Supervised  Solu#on     •  Training data:  Record  experts  game   sessions   •  Target label:  Ac0on  experts  take  at  every   step   •  What  if  there’s  no  expert?   •  This  is  not  how  human  learns   Problems:   slides  by     Yen-­‐Chen  Lin  
How  Human  Learns   •  Don’t  need  somebody  to  tell  us  a  million   0mes  which  move  to  choose  at  each  screen   •  Just  need  occasional feedback  that  we   did  the  right  thing   slides  by     Yen-­‐Chen  Lin  
Reinforcement  Learning   •  Somewhere  between  supervised  and   unsupervised  learning   •  Sparse  and  time-delayed  labels   Based  only  on  those  rewards,  the  agent  has   to  learn  to  behave  in  the  environment.     A  ra0onal  agent  should  op0mize  total   reward.   slides  by     Yen-­‐Chen  Lin  
RL  in  A  Nutshell   slides  by     Yen-­‐Chen  Lin  
Markov  Decision  Process   •  State     •  Action     •  Reward The  probability  of  the  next  state  si+1  depends  only  on   current  state  si  and  ac0on  ai. slides  by     Yen-­‐Chen  Lin  
Episode   One  episode  of  this  process  (e.g.  one  game)  forms  a   finite  sequence  of  states,  ac0ons  and  rewards:   slides  by     Yen-­‐Chen  Lin  
Example:  Breakout   •  State: game  screen     •  Action:
 
 
 •  Reward:  game  score   1. do  nothing   2.  le6   3.  right   slides  by     Yen-­‐Chen  Lin  
Example:  Breakout   •  State: successive 
 game  screens     •  Action:
 
 
 •  Reward:  game  score   1. do  nothing   2.  le6   3.  right   slides  by     Yen-­‐Chen  Lin  
•  To  perform  well,  we  should  also  take  future   rewards  into  account,  how  to  do  that?   Total reward: Total future reward: Reward   slides  by     Yen-­‐Chen  Lin  
Discounted  Future  Reward   •  However,  since  the  environment  is   stochas0c,  intui0vely  one  should  earn   reward  as  soon  as  possible   Total discounted future reward: slides  by     Yen-­‐Chen  Lin  
Q  func#on   •  Q(s, a): The  maximum discounted future reward     when  we  perform  ac0on  a  in  state  s,     and  con0nue  optimally  from  that  point  on.   It represents the “quality” of a certain action in a given state. slides  by     Yen-­‐Chen  Lin  
How  to  Choose  Ac#on?   Here  π  represents  the  policy,     the  rule  how  we  choose  an  ac0on  in  each  state.   If  we  know  Q  func0on,   slides  by     Yen-­‐Chen  Lin  
Q  Func#on  Implementa#on   ac#on  0   ac#on  1   ac#on  2   state  0   -­‐2   -­‐1   5   state  1   3   2   3   state  2   5   6   -­‐6   slides  by     Yen-­‐Chen  Lin  
If  We  Use  Pixels  as  State   1.  Resize  images  to  84x84   2.  Convert  to  grayscale  with  256  levels   3.  Use  last  4  frames  to  represent  state   25684x84x4  =  1067970      possible  game  states   We  can  never  cover  all  the  cases!   slides  by     Yen-­‐Chen  Lin  
Vision  &  Controal:  Deep  Q  Network   We  use  CNN  to  represent  Q  func0on,  which  takes:   •  Input:  the  state  (4  game  screens)  and  ac0on   •  Output:  Q-­‐values  of  different  ac0ons  a  (i.e.,  Q(s,a))   slides  by     Yen-­‐Chen  Lin   π(              )=argmaxaQ(                ,a)    
Fusing  Mul#ple  Sensors   Ke#le% Medium+wrap% Ke#le% Medium+wrap% thumb+4+finger% Manipula7on% Region% Side+view% Chan  et  al.  ECCV  2015  from  VSLab  
Left Hand Head Right Hand 81 Lab Office Home
Left Hand Head Right Hand 82 Lab Office Home
Recogni#on  from  Wearable  Cameras   Pred% GT% Pred% GT% Gesture%Recogni1on% Object%Category%Recogni1on%
Real-­‐#me  Wearable  Demo   Fisheye  camera   NVIDIA  TK1  
Real-­‐#me  Wearable  Demo   cellphone,  bo2le,  keyboard,  mouse,  free  hand  
Take-­‐Home  Message   •  Encoding  Source  (data)   – N-­‐D  observa0on   – N-­‐D  sequence  of  observa0ons   •  Decoding  Outcome  (AI  tasks)   – N-­‐D  single  output   – N-­‐D  open-­‐ended  sequence  as  output     •  Mul0ple  Encoding  and  Decoding   •  If  each  module  is  differen0able/approximately   differen0able  -­‐>  End-­‐to-­‐End  Learning   We  get  many  tools  to  tackle   Ar#ficial  General  Intelligence     Just  Try!   Worse  Thing:  Do  Nothing  
My  Two  Cents  for  Taiwan  
Ques#ons   •  Can  I  simply  ask  my  engineers  to  use   open  source  deep  learning  tools  to   create  new  products?   Answer:  Yes  and  Not  really.   Yes  –  if  you  want  to  complete  a  well-­‐known   task.  But  Google’s  MLaaS  product  will  almost   always  beat  you.   Not  really  –  if  you  want  to  solve  your  own   problem,  with  your  own  data.  You  need  talents   or  make  engineers  not  afraid  of  failure.  
Where  can  I  find  talents?   •  Most  talents  are  PhD  students  or  young   professionals  in  the  US  and  EU.   h2p://www.economist.com/news/business/21695908-­‐silicon-­‐valley-­‐fights-­‐talent-­‐universi0es-­‐struggle-­‐hold-­‐their   How  can  we  compete?  
Local  Students   •  Our  students  know  deep  learning  is  HOT!   [  Deep  Learning  Workshop  中研院  ]  500  位參加者  
Case  Study:  NTHU@TW  Undergraduate   h2ps://github.com/yenchenlin1994/DeepLearningFlappyBird  
Case  Study:  UNIST@Korean  Undergraduate  
To-­‐Do  for  Local  Students   •  We  need  more  students  to  work  on     – realis0c  deep  learning  projects  with     – enough  computer  resource   •  We  need  some  of  them  to  stay  in  our  local   industry   Advanced  Deep  Learning  Course  at  NTHU  (105學年)   1.  Taught  by  a  group  of  profs   2.  Topics  including  latest  DNN  models,  distributed   training,  DL  for  embedded  system   3.  Sponsored  by  MTK  and  ITRI  巨資中心   4.  More  sponsors  are  welcomed!  
For  Talents  Abroad   Get  in  the  Talents  Race!   h2p://cvpr2016.thecvf.com/exhibit/industry_expo  
For  Talents  Abroad   Most  of  them  fresh  PhDs   1  Billion  Pledged  USD  
For  Talents  Abroad  
AI  is  happening  Fast  
Thanks!  

Recommended

李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習台灣資料科學年會
 
[系列活動] 一日搞懂生成式對抗網路
[系列活動] 一日搞懂生成式對抗網路[系列活動] 一日搞懂生成式對抗網路
[系列活動] 一日搞懂生成式對抗網路台灣資料科學年會
 
Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Alexander Korbonits
 
[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習台灣資料科學年會
 
An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)Thomas da Silva Paula
 
What Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceWhat Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceJonathan Mugan
 
What Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceWhat Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceJonathan Mugan
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionTe-Yen Liu
 

Recommended

李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習李宏毅/當語音處理遇上深度學習
李宏毅/當語音處理遇上深度學習台灣資料科學年會
 
[系列活動] 一日搞懂生成式對抗網路
[系列活動] 一日搞懂生成式對抗網路[系列活動] 一日搞懂生成式對抗網路
[系列活動] 一日搞懂生成式對抗網路台灣資料科學年會
 
Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Alexander Korbonits
 
[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動：李宏毅 / 一天搞懂深度學習台灣資料科學年會
 
An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)Thomas da Silva Paula
 
What Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceWhat Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceJonathan Mugan
 
What Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceWhat Deep Learning Means for Artificial Intelligence
What Deep Learning Means for Artificial IntelligenceJonathan Mugan
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionTe-Yen Liu
 
Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesTuri, Inc.
 
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.
 
Deeplearning in finance
Deeplearning in financeDeeplearning in finance
Deeplearning in financeSebastien Jehan
 
Deep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsDeep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsBenjamin Le
 
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Greg Makowski
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
Deep learning
Deep learningDeep learning
Deep learningPratap Dangeti
 
[系列活動] 手把手的深度學實務
[系列活動] 手把手的深度學實務[系列活動] 手把手的深度學實務
[系列活動] 手把手的深度學實務台灣資料科學年會
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
 
Multimodal Learning Analytics
Multimodal Learning AnalyticsMultimodal Learning Analytics
Multimodal Learning AnalyticsXavier Ochoa
 
Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial Alexandros Karatzoglou
 
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsDeep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsJason Tsai
 
Deep Learning through Examples
Deep Learning through ExamplesDeep Learning through Examples
Deep Learning through ExamplesSri Ambati
 
[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machines[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machinesNAVER D2
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learninginside-BigData.com
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksMark Scully
 
[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用台灣資料科學年會
 
Deep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural ZooDeep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural ZooChristian Perone
 
[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVERNAVER D2
 
海量視覺資料－孫民
海量視覺資料－孫民海量視覺資料－孫民
海量視覺資料－孫民台灣資料科學年會
 
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室台灣資料科學年會
 

More Related Content

What's hot

Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesTuri, Inc.
 
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 for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsDeep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsBenjamin Le
 
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Greg Makowski
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
[系列活動] 手把手的深度學實務
[系列活動] 手把手的深度學實務[系列活動] 手把手的深度學實務
[系列活動] 手把手的深度學實務台灣資料科學年會
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
 
Multimodal Learning Analytics
Multimodal Learning AnalyticsMultimodal Learning Analytics
Multimodal Learning AnalyticsXavier Ochoa
 
Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial Alexandros Karatzoglou
 
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsDeep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsJason Tsai
 
Deep Learning through Examples
Deep Learning through ExamplesDeep Learning through Examples
Deep Learning through ExamplesSri Ambati
 
[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machines[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machinesNAVER D2
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksMark Scully
 
[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用台灣資料科學年會
 
Deep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural ZooDeep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural ZooChristian Perone
 
[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVERNAVER D2
 

What's hot (20)

Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep Features
 
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
 
Deeplearning in finance
Deeplearning in financeDeeplearning in finance
Deeplearning in finance
 
Deep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsDeep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender Systems
 
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
Using Deep Learning to do Real-Time Scoring in Practical Applications - 2015-...
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016
 
Deep learning
Deep learningDeep learning
Deep learning
 
[系列活動] 手把手的深度學實務
[系列活動] 手把手的深度學實務[系列活動] 手把手的深度學實務
[系列活動] 手把手的深度學實務
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
 
Multimodal Learning Analytics
Multimodal Learning AnalyticsMultimodal Learning Analytics
Multimodal Learning Analytics
 
Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial Deep Learning for Recommender Systems RecSys2017 Tutorial
Deep Learning for Recommender Systems RecSys2017 Tutorial
 
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsDeep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
 
Deep Learning through Examples
Deep Learning through ExamplesDeep Learning through Examples
Deep Learning through Examples
 
[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machines[246]reasoning, attention and memory toward differentiable reasoning machines
[246]reasoning, attention and memory toward differentiable reasoning machines
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learning
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural Networks
 
[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用[系列活動] 人工智慧與機器學習在推薦系統上的應用
[系列活動] 人工智慧與機器學習在推薦系統上的應用
 
Deep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural ZooDeep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural Zoo
 
[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER
 

Viewers also liked

吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室台灣資料科學年會
 
天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統
天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統
天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統台灣資料科學年會
 
一個賭徒的告白：從預測市場看金融交易
一個賭徒的告白：從預測市場看金融交易一個賭徒的告白：從預測市場看金融交易
一個賭徒的告白：從預測市場看金融交易台灣資料科學年會
 
姜俊宇/從資料到知識：從零開始的資料探勘
姜俊宇/從資料到知識：從零開始的資料探勘姜俊宇/從資料到知識：從零開始的資料探勘
姜俊宇/從資料到知識：從零開始的資料探勘台灣資料科學年會
 
吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？
吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？
吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？台灣資料科學年會
 
從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪
從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪
從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪台灣資料科學年會
 
[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單
[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單
[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單台灣資料科學年會
 
[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務
[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務
[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務台灣資料科學年會
 
手把手教你 R 語言資料分析實務/張毓倫&陳柏亨
手把手教你 R 語言資料分析實務/張毓倫&陳柏亨手把手教你 R 語言資料分析實務/張毓倫&陳柏亨
手把手教你 R 語言資料分析實務/張毓倫&陳柏亨台灣資料科學年會
 
[系列活動] 給工程師的統計學及資料分析 123
[系列活動] 給工程師的統計學及資料分析 123[系列活動] 給工程師的統計學及資料分析 123
[系列活動] 給工程師的統計學及資料分析 123台灣資料科學年會
 
[系列活動] 手把手教你R語言資料分析實務
[系列活動] 手把手教你R語言資料分析實務[系列活動] 手把手教你R語言資料分析實務
[系列活動] 手把手教你R語言資料分析實務台灣資料科學年會
 
[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用
[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用
[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用台灣資料科學年會
 
[系列活動] Machine Learning 機器學習課程
[系列活動] Machine Learning 機器學習課程[系列活動] Machine Learning 機器學習課程
[系列活動] Machine Learning 機器學習課程台灣資料科學年會
 
[系列活動] 使用 R 語言建立自己的演算法交易事業
[系列活動] 使用 R 語言建立自己的演算法交易事業[系列活動] 使用 R 語言建立自己的演算法交易事業
[系列活動] 使用 R 語言建立自己的演算法交易事業台灣資料科學年會
 
給軟體工程師的不廢話 R 語言精要班
給軟體工程師的不廢話 R 語言精要班給軟體工程師的不廢話 R 語言精要班
給軟體工程師的不廢話 R 語言精要班台灣資料科學年會
 
[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹
[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹
[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹台灣資料科學年會
 
Big-data analytics: challenges and opportunities
Big-data analytics: challenges and opportunitiesBig-data analytics: challenges and opportunities
Big-data analytics: challenges and opportunities台灣資料科學年會
 

Viewers also liked (20)

海量視覺資料－孫民
海量視覺資料－孫民海量視覺資料－孫民
海量視覺資料－孫民
 
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
吳齊軒/漫談 R 的學習挑戰與 R 語言翻轉教室
 
天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統
天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統
天下武功唯快不破：利用串流資料實做出即時分類器和即時推薦系統
 
一個賭徒的告白：從預測市場看金融交易
一個賭徒的告白：從預測市場看金融交易一個賭徒的告白：從預測市場看金融交易
一個賭徒的告白：從預測市場看金融交易
 
姜俊宇/從資料到知識：從零開始的資料探勘
姜俊宇/從資料到知識：從零開始的資料探勘姜俊宇/從資料到知識：從零開始的資料探勘
姜俊宇/從資料到知識：從零開始的資料探勘
 
吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？
吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？
吳牧恩/一個賭徒的告白 2：交易策略建構與分析，為何你該賭小一點？
 
從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪
從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪
從網頁存取記錄瞭解使用者行為與網頁區塊貢獻分析－崔殷豪
 
Learning for Big Data－林軒田
Learning for Big Data－林軒田Learning for Big Data－林軒田
Learning for Big Data－林軒田
 
[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單
[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單
[DSC 2016] 系列活動：吳牧恩、林佳緯 / 用 R 輕鬆做交易策略分析及自動下單
 
[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務
[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務
[DSC 2016] 系列活動：許懷中 / R 語言資料探勘實務
 
手把手教你 R 語言資料分析實務/張毓倫&陳柏亨
手把手教你 R 語言資料分析實務/張毓倫&陳柏亨手把手教你 R 語言資料分析實務/張毓倫&陳柏亨
手把手教你 R 語言資料分析實務/張毓倫&陳柏亨
 
[系列活動] 給工程師的統計學及資料分析 123
[系列活動] 給工程師的統計學及資料分析 123[系列活動] 給工程師的統計學及資料分析 123
[系列活動] 給工程師的統計學及資料分析 123
 
[系列活動] 手把手教你R語言資料分析實務
[系列活動] 手把手教你R語言資料分析實務[系列活動] 手把手教你R語言資料分析實務
[系列活動] 手把手教你R語言資料分析實務
 
[系列活動] 機器學習速遊
[系列活動] 機器學習速遊[系列活動] 機器學習速遊
[系列活動] 機器學習速遊
 
[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用
[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用
[DSC x TAAI 2016] 林守德 / 人工智慧與機器學習在推薦系統上的應用
 
[系列活動] Machine Learning 機器學習課程
[系列活動] Machine Learning 機器學習課程[系列活動] Machine Learning 機器學習課程
[系列活動] Machine Learning 機器學習課程
 
[系列活動] 使用 R 語言建立自己的演算法交易事業
[系列活動] 使用 R 語言建立自己的演算法交易事業[系列活動] 使用 R 語言建立自己的演算法交易事業
[系列活動] 使用 R 語言建立自己的演算法交易事業
 
給軟體工程師的不廢話 R 語言精要班
給軟體工程師的不廢話 R 語言精要班給軟體工程師的不廢話 R 語言精要班
給軟體工程師的不廢話 R 語言精要班
 
[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹
[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹
[系列活動] 無所不在的自然語言處理—基礎概念、技術與工具介紹
 
Big-data analytics: challenges and opportunities
Big-data analytics: challenges and opportunitiesBig-data analytics: challenges and opportunities
Big-data analytics: challenges and opportunities
 

Similar to 孫民/從電腦視覺看人工智慧 : 下一件大事

LST Toolkit: Exfiltration Over Sound, Light, Touch
LST Toolkit: Exfiltration Over Sound, Light, TouchLST Toolkit: Exfiltration Over Sound, Light, Touch
LST Toolkit: Exfiltration Over Sound, Light, TouchDimitry Snezhkov
 
Sippin: A Mobile Application Case Study presented at Techfest Louisville
Sippin: A Mobile Application Case Study presented at Techfest LouisvilleSippin: A Mobile Application Case Study presented at Techfest Louisville
Sippin: A Mobile Application Case Study presented at Techfest LouisvilleDawn Yankeelov
 
iOS Scroll Performance
iOS Scroll PerformanceiOS Scroll Performance
iOS Scroll PerformanceKyle Sherman
 
Using Deep Learning to do Real-Time Scoring in Practical Applications
Using Deep Learning to do Real-Time Scoring in Practical ApplicationsUsing Deep Learning to do Real-Time Scoring in Practical Applications
Using Deep Learning to do Real-Time Scoring in Practical ApplicationsGreg Makowski
 
Yuandong Tian at AI Frontiers : Planning in Reinforcement Learning
Yuandong Tian at AI Frontiers : Planning in Reinforcement LearningYuandong Tian at AI Frontiers : Planning in Reinforcement Learning
Yuandong Tian at AI Frontiers : Planning in Reinforcement LearningAI Frontiers
 
“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...
“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...
“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...Edge AI and Vision Alliance
 
J-Fall 2017 - AI Self-learning Game Playing
J-Fall 2017 - AI Self-learning Game PlayingJ-Fall 2017 - AI Self-learning Game Playing
J-Fall 2017 - AI Self-learning Game PlayingRichard Abbuhl
 
AlphaZero and beyond: Polygames
AlphaZero and beyond: PolygamesAlphaZero and beyond: Polygames
AlphaZero and beyond: PolygamesOlivier Teytaud
 
Story points considered harmful - or why the future of estimation is really i...
Story points considered harmful - or why the future of estimation is really i...Story points considered harmful - or why the future of estimation is really i...
Story points considered harmful - or why the future of estimation is really i...Vasco Duarte
 
Devoxx 2017 - AI Self-learning Game Playing
Devoxx 2017 - AI Self-learning Game PlayingDevoxx 2017 - AI Self-learning Game Playing
Devoxx 2017 - AI Self-learning Game PlayingRichard Abbuhl
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer FarooquiDatabricks
 
Five Cliches of Online Game Development
Five Cliches of Online Game DevelopmentFive Cliches of Online Game Development
Five Cliches of Online Game Developmentiandundore
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for RoboticsIntel Nervana
 
[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...
[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...
[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...GangSeok Lee
 

Similar to 孫民/從電腦視覺看人工智慧 : 下一件大事 (20)

LST Toolkit: Exfiltration Over Sound, Light, Touch
LST Toolkit: Exfiltration Over Sound, Light, TouchLST Toolkit: Exfiltration Over Sound, Light, Touch
LST Toolkit: Exfiltration Over Sound, Light, Touch
 
Sippin: A Mobile Application Case Study presented at Techfest Louisville
Sippin: A Mobile Application Case Study presented at Techfest LouisvilleSippin: A Mobile Application Case Study presented at Techfest Louisville
Sippin: A Mobile Application Case Study presented at Techfest Louisville
 
Scaling Deep Learning
Scaling Deep LearningScaling Deep Learning
Scaling Deep Learning
 
專題報告
專題報告專題報告
專題報告
 
DL (v2).pptx
DL (v2).pptxDL (v2).pptx
DL (v2).pptx
 
iOS Scroll Performance
iOS Scroll PerformanceiOS Scroll Performance
iOS Scroll Performance
 
Using Deep Learning to do Real-Time Scoring in Practical Applications
Using Deep Learning to do Real-Time Scoring in Practical ApplicationsUsing Deep Learning to do Real-Time Scoring in Practical Applications
Using Deep Learning to do Real-Time Scoring in Practical Applications
 
Yuandong Tian at AI Frontiers : Planning in Reinforcement Learning
Yuandong Tian at AI Frontiers : Planning in Reinforcement LearningYuandong Tian at AI Frontiers : Planning in Reinforcement Learning
Yuandong Tian at AI Frontiers : Planning in Reinforcement Learning
 
“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...
“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...
“Reinforcement Learning: a Practical Introduction,” a Presentation from Micro...
 
J-Fall 2017 - AI Self-learning Game Playing
J-Fall 2017 - AI Self-learning Game PlayingJ-Fall 2017 - AI Self-learning Game Playing
J-Fall 2017 - AI Self-learning Game Playing
 
AlphaZero and beyond: Polygames
AlphaZero and beyond: PolygamesAlphaZero and beyond: Polygames
AlphaZero and beyond: Polygames
 
Story points considered harmful - or why the future of estimation is really i...
Story points considered harmful - or why the future of estimation is really i...Story points considered harmful - or why the future of estimation is really i...
Story points considered harmful - or why the future of estimation is really i...
 
An Introduction to Face Detection
An Introduction to Face DetectionAn Introduction to Face Detection
An Introduction to Face Detection
 
Devoxx 2017 - AI Self-learning Game Playing
Devoxx 2017 - AI Self-learning Game PlayingDevoxx 2017 - AI Self-learning Game Playing
Devoxx 2017 - AI Self-learning Game Playing
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 
data science
data sciencedata science
data science
 
Five Cliches of Online Game Development
Five Cliches of Online Game DevelopmentFive Cliches of Online Game Development
Five Cliches of Online Game Development
 
Deep Learning for Robotics
Deep Learning for RoboticsDeep Learning for Robotics
Deep Learning for Robotics
 
[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...
[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...
[2010 CodeEngn Conference 04] passket - Taint analysis for vulnerability disc...
 
Data Science
Data Science Data Science
Data Science
 

More from 台灣資料科學年會

[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用台灣資料科學年會
 
[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告台灣資料科學年會
 
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰台灣資料科學年會
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機台灣資料科學年會
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機台灣資料科學年會
 
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話台灣資料科學年會
 
[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇台灣資料科學年會
 
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察 [TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察 台灣資料科學年會
 
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵台灣資料科學年會
 
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用台灣資料科學年會
 
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告台灣資料科學年會
 
[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話台灣資料科學年會
 
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人台灣資料科學年會
 
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維台灣資料科學年會
 
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察台灣資料科學年會
 
[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰台灣資料科學年會
 
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT台灣資料科學年會
 
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達台灣資料科學年會
 
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳台灣資料科學年會
 

More from 台灣資料科學年會 (20)

[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用[台灣人工智慧學校] 人工智慧技術發展與應用
[台灣人工智慧學校] 人工智慧技術發展與應用
 
[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告[台灣人工智慧學校] 執行長報告
[台灣人工智慧學校] 執行長報告
 
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
[台灣人工智慧學校] 工業 4.0 與智慧製造的發展趨勢與挑戰
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
 
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
[台灣人工智慧學校] 開創台灣產業智慧轉型的新契機
 
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
[台灣人工智慧學校] 台北總校第三期結業典禮 - 執行長談話
 
[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇
[TOxAIA台中分校] AI 引爆新工業革命，智慧機械首都台中轉型論壇
 
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察 [TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
[TOxAIA台中分校] 2019 台灣數位轉型 與產業升級趨勢觀察
 
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
[TOxAIA台中分校] 智慧製造成真! 產線導入AI的致勝關鍵
 
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用[台灣人工智慧學校] 從經濟學看人工智慧產業應用
[台灣人工智慧學校] 從經濟學看人工智慧產業應用
 
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
[台灣人工智慧學校] 台中分校第二期開學典禮 - 執行長報告
 
台灣人工智慧學校成果發表會
台灣人工智慧學校成果發表會台灣人工智慧學校成果發表會
台灣人工智慧學校成果發表會
 
[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話[台中分校] 第一期結業典禮 - 執行長談話
[台中分校] 第一期結業典禮 - 執行長談話
 
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
[TOxAIA新竹分校] 工業4.0潛力新應用! 多模式對話機器人
 
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
[TOxAIA新竹分校] AI整合是重點! 竹科的關鍵轉型思維
 
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
[TOxAIA新竹分校] 2019 台灣數位轉型與產業升級趨勢觀察
 
[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰[TOxAIA新竹分校] 深度學習與Kaggle實戰
[TOxAIA新竹分校] 深度學習與Kaggle實戰
 
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
[台灣人工智慧學校] Bridging AI to Precision Agriculture through IoT
 
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達
[2018 台灣人工智慧學校校友年會] 產業經驗分享: 如何用最少的訓練樣本，得到最好的深度學習影像分析結果，減少一半人力，提升一倍品質 / 李明達
 
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
[2018 台灣人工智慧學校校友年會] 啟動物聯網新關鍵 - 未來由你「喚」醒 / 沈品勳
 

Recently uploaded

DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Seán Kennedy
 
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...ssuserf63bd7
 
Advanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsAdvanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsVICTOR MAESTRE RAMIREZ
 
Heart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectHeart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectBoston Institute of Analytics
 
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSINGmarianagonzalez07
 
1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPTBoston Institute of Analytics
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxMike Bennett
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxNLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxBoston Institute of Analytics
 
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...Amil Baba Dawood bangali
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Cathrine Wilhelmsen
 

Recently uploaded (20)

DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...
 
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
Statistics, Data Analysis, and Decision Modeling, 5th edition by James R. Eva...
 
Advanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsAdvanced Machine Learning for Business Professionals
Advanced Machine Learning for Business Professionals
 
Heart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectHeart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis Project
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
 
1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证）昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptx
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptxNLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
NLP Project PPT: Flipkart Product Reviews through NLP Data Science.pptx
 
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)
 

孫民/從電腦視覺看人工智慧 : 下一件大事

  • 1. Ar#ficial  Intelligence:     The  Next  Big  Thing     from  a  computer  vision  perspec0ve     VSLab   清大電機 孫民
  • 2. What’s  the  Next  Big  Thing?   h2p://research.microso6.com/en-­‐us/um/redmond/events/fs2015  
  • 3. Goal     “big  data  being  the  source,  machine   learning  being  the  technique,  and  AI   being  the  outcome”     by  Prof.  Hsuan-­‐Tien  Lin  at  IEEE  BigData  2016     Many  kinds  of  source  (data)  and   outcomes  (AI  tasks)  can  be  trained  end-­‐ to-­‐end  using  Deep  Learning  (DL)  
  • 4. Classical  AI  Tests:  Turing  Test   by  Alan  Turing  in  1950  
  • 6. Classical  AI  Tests:  CAPTCHA  
  • 7. Breaking  CAPTCHA   by  vicarious.com  
  • 8. AlphaGo   2016  by  Google  DeepMind   Are  these  what  AI  all  about?  
  • 10. 2015   Ar#fical  General  Intelligence  (AGI)  
  • 11. Deep  Learning  (DL)   •  Data   •  GPU  Compu0ng   •  Talents  
  • 12. DL  Fuses  AI-­‐subfields   •  Vision  and  Language     •  Vision  and  Control   h2p://mscoco.org/   Atari  Breakout  game  &  AlphaGo,  DeepMind.   -­‐>  AGI   •  Mul0ple  Encoding  and  Decoding  
  • 13. Image  Cap#oning   f(                      )  =   The  man  at  bat  is   ready  to  swing     at  the  pitch   Vision   Language   Recurrent  Neuron  Network  (RNN)   credit:  Nature   convolu0ons   Convolu#on  Neuron  Network  (CNN)   credit:  wiki  
  • 14. Image  Ques#on  Answering   h2p://visualqa.org/  
  • 15. Zhen  et  al.  ECCV  2016  from  VSLab  and  Stanford  AI  Lab  
  • 16. Big  Video  Data  with  Titles   •  Pairs  of   Raw  Video     CNN   CNN   CNN   CNN   Title  
  • 17. Viral  Videos   Google  for  “viral  video  company”  
  • 18. Large  Video  Repository   Currently  28740  videos  and  keep  growing  
  • 19. DL  Fuses  AI-­‐subfields   •  Vision  and  Language     •  Vision  and  Control   h2p://mscoco.org/   Atari  Breakout  game  &  AlphaGo,  DeepMind.   -­‐>  AGI   •  Mul0ple  Encoding  and  Decoding  
  • 20. Vision  and  Control   h2ps://gym.openai.com/   •  Learning  to  play  game  with  weak  supervision:    Reinforcement  Learning  (RL)  
  • 21. Where  It  All  Begins  …     by  DeepMind  in  NIPS  2013  Deep  Learning  Wrokshop   Playing Atari with Deep Reinforcement Learning slides  by     Yen-­‐Chen  Lin  
  • 22. Control:  Learning  to  Act   Play  Breakout  equals  to   •  Input:  screen  images   •  Output:  ac0ons          (do  nothing  |  left  |  right)     Supervised   Classifica0on   slides  by     Yen-­‐Chen  Lin  
  • 23. Supervised  Solu#on     •  Training data:  Record  experts  game   sessions   •  Target label:  Ac0on  experts  take  at  every   step   •  What  if  there’s  no  expert?   •  This  is  not  how  human  learns   Problems:   slides  by     Yen-­‐Chen  Lin  
  • 24. How  Human  Learns   •  Don’t  need  somebody  to  tell  us  a  million   0mes  which  move  to  choose  at  each  screen   •  Just  need  occasional feedback  that  we   did  the  right  thing   slides  by     Yen-­‐Chen  Lin  
  • 25. Reinforcement  Learning   •  Somewhere  between  supervised  and   unsupervised  learning   •  Sparse  and  time-delayed  labels   Based  only  on  those  rewards,  the  agent  has   to  learn  to  behave  in  the  environment.     A  ra0onal  agent  should  op0mize  total   reward.   slides  by     Yen-­‐Chen  Lin  
  • 26. RL  in  A  Nutshell   slides  by     Yen-­‐Chen  Lin  
  • 27. Markov  Decision  Process   •  State     •  Action     •  Reward The  probability  of  the  next  state  si+1  depends  only  on   current  state  si  and  ac0on  ai. slides  by     Yen-­‐Chen  Lin  
  • 28. Episode   One  episode  of  this  process  (e.g.  one  game)  forms  a   finite  sequence  of  states,  ac0ons  and  rewards:   slides  by     Yen-­‐Chen  Lin  
  • 29. Example:  Breakout   •  State: game  screen     •  Action:
 
 
 •  Reward:  game  score   1. do  nothing   2.  le6   3.  right   slides  by     Yen-­‐Chen  Lin  
  • 30. Example:  Breakout   •  State: successive 
 game  screens     •  Action:
 
 
 •  Reward:  game  score   1. do  nothing   2.  le6   3.  right   slides  by     Yen-­‐Chen  Lin  
  • 31. •  To  perform  well,  we  should  also  take  future   rewards  into  account,  how  to  do  that?   Total reward: Total future reward: Reward   slides  by     Yen-­‐Chen  Lin  
  • 32. Discounted  Future  Reward   •  However,  since  the  environment  is   stochas0c,  intui0vely  one  should  earn   reward  as  soon  as  possible   Total discounted future reward: slides  by     Yen-­‐Chen  Lin  
  • 33. Q  func#on   •  Q(s, a): The  maximum discounted future reward     when  we  perform  ac0on  a  in  state  s,     and  con0nue  optimally  from  that  point  on.   It represents the “quality” of a certain action in a given state. slides  by     Yen-­‐Chen  Lin  
  • 34. How  to  Choose  Ac#on?   Here  π  represents  the  policy,     the  rule  how  we  choose  an  ac0on  in  each  state.   If  we  know  Q  func0on,   slides  by     Yen-­‐Chen  Lin  
  • 35. Q  Func#on  Implementa#on   ac#on  0   ac#on  1   ac#on  2   state  0   -­‐2   -­‐1   5   state  1   3   2   3   state  2   5   6   -­‐6   slides  by     Yen-­‐Chen  Lin  
  • 36. If  We  Use  Pixels  as  State   1.  Resize  images  to  84x84   2.  Convert  to  grayscale  with  256  levels   3.  Use  last  4  frames  to  represent  state   25684x84x4  =  1067970      possible  game  states   We  can  never  cover  all  the  cases!   slides  by     Yen-­‐Chen  Lin  
  • 37. Vision  &  Controal:  Deep  Q  Network   We  use  CNN  to  represent  Q  func0on,  which  takes:   •  Input:  the  state  (4  game  screens)  and  ac0on   •  Output:  Q-­‐values  of  different  ac0ons  a  (i.e.,  Q(s,a))   slides  by     Yen-­‐Chen  Lin   π(              )=argmaxaQ(                ,a)    
  • 38. Fusing  Mul#ple  Sensors   Ke#le% Medium+wrap% Ke#le% Medium+wrap% thumb+4+finger% Manipula7on% Region% Side+view% Chan  et  al.  ECCV  2015  from  VSLab  
  • 39. Left Hand Head Right Hand 81 Lab Office Home
  • 40. Left Hand Head Right Hand 82 Lab Office Home
  • 41. Recogni#on  from  Wearable  Cameras   Pred% GT% Pred% GT% Gesture%Recogni1on% Object%Category%Recogni1on%
  • 42. Real-­‐#me  Wearable  Demo   Fisheye  camera   NVIDIA  TK1  
  • 43. Real-­‐#me  Wearable  Demo   cellphone,  bo2le,  keyboard,  mouse,  free  hand  
  • 44. Take-­‐Home  Message   •  Encoding  Source  (data)   – N-­‐D  observa0on   – N-­‐D  sequence  of  observa0ons   •  Decoding  Outcome  (AI  tasks)   – N-­‐D  single  output   – N-­‐D  open-­‐ended  sequence  as  output     •  Mul0ple  Encoding  and  Decoding   •  If  each  module  is  differen0able/approximately   differen0able  -­‐>  End-­‐to-­‐End  Learning   We  get  many  tools  to  tackle   Ar#ficial  General  Intelligence     Just  Try!   Worse  Thing:  Do  Nothing  
  • 45. My  Two  Cents  for  Taiwan  
  • 46. Ques#ons   •  Can  I  simply  ask  my  engineers  to  use   open  source  deep  learning  tools  to   create  new  products?   Answer:  Yes  and  Not  really.   Yes  –  if  you  want  to  complete  a  well-­‐known   task.  But  Google’s  MLaaS  product  will  almost   always  beat  you.   Not  really  –  if  you  want  to  solve  your  own   problem,  with  your  own  data.  You  need  talents   or  make  engineers  not  afraid  of  failure.  
  • 47. Where  can  I  find  talents?   •  Most  talents  are  PhD  students  or  young   professionals  in  the  US  and  EU.   h2p://www.economist.com/news/business/21695908-­‐silicon-­‐valley-­‐fights-­‐talent-­‐universi0es-­‐struggle-­‐hold-­‐their   How  can  we  compete?  
  • 48. Local  Students   •  Our  students  know  deep  learning  is  HOT!   [  Deep  Learning  Workshop  中研院  ]  500  位參加者  
  • 49. Case  Study:  NTHU@TW  Undergraduate   h2ps://github.com/yenchenlin1994/DeepLearningFlappyBird  
  • 50. Case  Study:  UNIST@Korean  Undergraduate  
  • 51. To-­‐Do  for  Local  Students   •  We  need  more  students  to  work  on     – realis0c  deep  learning  projects  with     – enough  computer  resource   •  We  need  some  of  them  to  stay  in  our  local   industry   Advanced  Deep  Learning  Course  at  NTHU  (105學年)   1.  Taught  by  a  group  of  profs   2.  Topics  including  latest  DNN  models,  distributed   training,  DL  for  embedded  system   3.  Sponsored  by  MTK  and  ITRI  巨資中心   4.  More  sponsors  are  welcomed!  
  • 52. For  Talents  Abroad   Get  in  the  Talents  Race!   h2p://cvpr2016.thecvf.com/exhibit/industry_expo  
  • 53. For  Talents  Abroad   Most  of  them  fresh  PhDs   1  Billion  Pledged  USD  
  • 55. AI  is  happening  Fast