SlideShare a Scribd company logo
Terry Taewoong Um (terry.t.um@gmail.com)
University of Waterloo
Department of Electrical & Computer Engineering
Terry Taewoong Um
DEEP LEARNING TUTORIAL
IN 100 MINS
1
Terry Taewoong Um (terry.t.um@gmail.com)
WHO AM I
2
2008 – 2010 M.S. at Seoul National University, Korea
c.f. “Tangent Space RRT with Lazy Projection: An Efficient Planning
Algorithm for Constrained Motions”, T. T. Um et al., ARK2010.
2010 – 2014 Robotics researcher at LIG Nex1 / KIST, Korea
c.f. “Independent Joint Learning: A Novel Task-to-Task Transfer Learning
Scheme for Robot Models”, T. T. Um et al., ICRA2014.
• I am a robotics researcher
Terry Taewoong Um (terry.t.um@gmail.com)
WHO AM I
3
2014 – Present PhD candidate at U.Waterloo, Canada
c.f. “Exercise Motion Classification from Large-Scale Wearable Sensor
Data Using Convolutional Neural Networks”, T. T. Um et al., IROS2017.
• I am a deep learning researcher
http://hookedoneverything.com/parkinsons/
https://www.trainwithpush.com/
PUSH project Parkinson’s disease (PD) project
WHO AM I
4
• But I am more known for ... - Facebook communities
: 로봇공학을 위한 열린 모임,
Tensorflow Korea, etc.
- Blog / Youtube
: 테리의 딥러닝 토크, T-Robotics,
대학원생 때 알았더라면
좋았을 이야기들
- Etc.
: Most-cited DL papers (github)
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
5
1. Introduction to ML & DL 50min
2. DL methods: CNN, RNN, VAE, GAN 35min
3. Can we believe DNNs? 15min
4. Q & A 15min
Break 10min
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
6
1. Introduction to ML & DL 50min
2. DL methods: CNN, RNN, VAE, GAN 35min
3. Can we believe DNNs? 15min
4. Q & A 15min
Break 10min
7
Terry Taewoong Um (terry.t.um@gmail.com)
https://github.com/sjchoi86/
dl_tutorials_10weeks
https://github.com/terryum/
awesome-deep-learning-papers
http://videolectures.net/
deeplearning2017_montreal/
• Deep learning summer school
STUDY MATERIALS
• Andrew Ng, Deeplearning.ai / Coursera
• Stanford Univ., CS231n (CNNs) / CS224d (RNNs)
• Various tutorials presented in NIPS, ICML, etc.
Terry Taewoong Um (terry.t.um@gmail.com)
8
AI, ML, DL, NN
https://medium.com/zeroth-ai/understanding-
artificial-intelligence-b9b58f9b25c2
Terry Taewoong Um (terry.t.um@gmail.com)
9
RECOGNITION - IMAGE
Google photos
Object recognition (image retrieval)
Terry Taewoong Um (terry.t.um@gmail.com)
10
YOLO v2, https://www.youtube.com/watch?v=VOC3huqHrss
RECOGNITION - IMAGE
Object detection
Terry Taewoong Um (terry.t.um@gmail.com)
11
RECOGNITION - NATURAL LANGUAGE
Sentiment classification
SAD Joyful
Terry Taewoong Um (terry.t.um@gmail.com)
12
Speech recognition
RECOGNITION - SPEECH
PUSH Inc., https://youtu.be/JpzuVPesFLY
Terry Taewoong Um (terry.t.um@gmail.com)
13
RECOGNITION - WEARABLES
Exercise recognition Parkinson’s disease assessment
Terry Taewoong Um (terry.t.um@gmail.com)
14
SUPERVISED LEARNING
Train : X → Y
image, text, speech,
wearable data, etc.
labels
Test : X → ?
(real practice)
* Never use the test dataset during the development of a model (training)
15
MODEL SELECTION
Terry Taewoong Um (terry.t.um@gmail.com)
16
OVERFITTING
good performance for training data
bad performance for test data
model complexity
error
training error
test error
• Model complexity vs. Error
Terry Taewoong Um (terry.t.um@gmail.com)
17
SUPERVISED LEARNING
Train : X → Y
image, text, speech,
wearable data, etc.
labels
Test : X → ?
(real practice)
* Never use the test dataset during the development of a model (training)
Terry Taewoong Um (terry.t.um@gmail.com)
18
VALIDATION SET
Train : X → Y
image, text, speech,
wearable data, etc.
labels
Validation : X → ?
(real-practice indicator)
Test : X → ?
(real practice)
Terry Taewoong Um (terry.t.um@gmail.com)
19
PREVENTING OVERFITTING
training time
error
training error
test error
we should
stop here
training
set
validation
set
test
set
for training
(parameter
optimization)
for early
stopping
(avoid
overfitting)
for evaluation
(measure the
performance)
keep watching the validation error
• Training / Validation / Test datasets
Terry Taewoong Um (terry.t.um@gmail.com)
20
PREVENTING OVERFITTING
training validation test
• N-fold cross validation
Terry Taewoong Um (terry.t.um@gmail.com)
21
BOLTS & NUTS OF BUILDING DL
http://www.computervisionblog.com/2016/12/
nuts-and-bolts-of-building-deep.html
Andrew Ng at NIPS2016
Terry Taewoong Um (terry.t.um@gmail.com)
22
REGULARIZATION
𝑚𝑖𝑛𝑖𝑚𝑖𝑧𝑒 σ ||𝑦 − 𝑓(𝑥)||2
, where,
𝑓 𝑥 = 𝑤0 + 𝑤1 𝑥1 + 𝑤2 𝑥2 + ⋯
= 𝑊𝑋
𝑚𝑖𝑛𝑖𝑚𝑖𝑧𝑒 ෍ ||𝑦 − 𝑓(𝑥)||2 + ||𝑊|| 𝑚
(minimize error & prefer a simpler model)
Terry Taewoong Um (terry.t.um@gmail.com)
23
GENERAL PROCEDURE OF ML
Task
Representation
(Features)
Feature
extraction
Machine
learning
IMAGE
SPEECH
Feature engineering
Terry Taewoong Um (terry.t.um@gmail.com)
24
WHAT ARE THE GOOD FEATURES?
http://twistedsifter.com/2016/03/puppy-or-bagel-meme-gallery/
Terry Taewoong Um (terry.t.um@gmail.com)
25
GENERAL PROCEDURE OF DL
Task
Representation
(Features)
Feature
extraction
Machine
learning
Task
Deep learning
(end-to-end)
* Feature
extraction included
Terry Taewoong Um (terry.t.um@gmail.com)
26
DEEP LEARNING
• What is Deep Learning (DL) ?
- Learning methods which have deep (not shallow) architecture
- It usually allows end-to-end learning
- It automatically learn intermediate representation. Thus,
it can be regarded as a representation learning
- It often contains stacked “neural network”. Thus,
Deep learning usually indicates “deep neural network”
“Deep Gaussian Process” (2013)
https://youtu.be/NwoGqYsQifg
http://goo.gl/fxmmPE
http://goo.gl/5Ry08S
Terry Taewoong Um (terry.t.um@gmail.com)
27
BIOLOGICAL EVIDENCE
Yann LeCun, https://goo.gl/VVQXJG
• The vental pathway in the visual cortex has multiple stages
• There exist a lot of intermediate representations
Terry Taewoong Um (terry.t.um@gmail.com)
28
IMAGENET CHALLENGE (ILSVRC)
http://image-net.org/challenges/talks/2016/ILSVRC2016_10_09_clsloc.pdf
• 1000 classes, 1.4 million images
• The first “large-scale” ML challenge
• Labeled by Amazon Mechanical Turk
(Fei-Fei Lee, Stanford Univ.)
• Need large-scale data → ImageNet
• Need a scalable method → DL
• Need computation power → GPU
• Convolutional Neural Networks (CNNs)
AlexNet (2012), VGG (2014), GoogLeNet
(2015), ResNet (2016), DenseNet (2017)...
29
NEURAL NETWORKS
Terry Taewoong Um (terry.t.um@gmail.com)
(H. Lalochelle, DLSS2017)
• A large parametric model
(like high-order polynomials)
• Learn the parameters using
gradient descent (GD) method
• Local minima problem? → Stochastic GD (SGD)
• Overfitting problem? → Large-scale data
30
NEURAL NETWORKS
Terry Taewoong Um (terry.t.um@gmail.com)
• Neural networks =
Composition of functions
Linear combination
𝑊𝑥 + 𝑏
Activation
σ(𝑊𝑥 + 𝑏)
(…repeat…)
Linear combination
𝑊 σ 𝑊(… ) + 𝑏 + 𝑏
Output activation
σ 𝑜𝑢𝑡 (… )
Forward pass Backward pass
Calculate the loss
Loss(𝑦𝑡𝑟𝑢𝑒, 𝑦 𝑝𝑟𝑒𝑑)
Gradient of the loss
Gradient of the activation
Gradient of the weights
(…repeat…)
Update the weights
(H. Lalochelle, DLSS2017)
ReLU or tanh
Softmax or Linear
Optimization:
SGD, RMSProb, or Adam
cross-entropy or MSE
Terry Taewoong Um (terry.t.um@gmail.com)
31
from keras.models import Sequential
from keras.layers import Dense
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=100))
model.add(Dense(units=10, activation='softmax’))
model.compile(loss='categorical_crossentropy',
optimizer='sgd’)
model.fit(x_train, y_train, epochs=5)
NN IN KERAS
• Recognition & Supervised learning
• Model selection & Overfitting
• Training set split & Cross validation
• Regularization
• Deep learning : End-to-end learning
• Neural Network Basics
Terry Taewoong Um (terry.t.um@gmail.com)
SUMMARY – PART1
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
33
1. Introduction to ML & DL 50min
2. DL methods: CNN, RNN, VAE, GAN 35min
3. Can we believe DNNs? 15min
4. Q & A 15min
Break 10min
34
POPULAR DL METHODS
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN)
Reinforcement learning
Deep Q-
Network
(DQN)
Actor-Critic
Policy gradient
Yuxi Li, “Deep reinforcement
learning: Overview”
https://arxiv.org/abs/1701.07274
35
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
Labels (O) Labels (X)
(mostly)
Discriminative model
(mostly)
Generative model
* RNN can be used as unsupervised manner
POPULAR DL METHODS
36
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Explicit
density
Implicit
density
(try to generate
realistic samples)
POPULAR DL METHODS
37
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Static
data
(e.g. image)
Sequence
data
(e.g. natural
language)
The area that I am
most familiar with
POPULAR DL METHODS
Explicit
density
Implicit
density
(try to generate
realistic samples)
38
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Static
data
(e.g. image)
Sequence
data
(e.g. natural
language)
POPULAR DL METHODS
Explicit
density
Implicit
density
(try to generate
realistic samples)
CONVOLUTIONAL NN (CNN)
Fully-connected layers Convolutional layers
w
h
n
39 / 39
p × 𝑞
Terry Taewoong Um (terry.t.um@gmail.com)
e.g.) (1k*1k) image * 1k nodes = 1 billion parameters [Fully-connected]
(3*3) kernel size * 64 kernels = 576 parameters [Convolutional]
https://github.com/vdumoulin
/conv_arithmetic
Terry Taewoong Um (terry.t.um@gmail.com)
40
• How can we deal with real images which is
much bigger than MNIST digit images?
- Use not fully-connected, but locally-connected NN
- Use convolutions to get various feature maps
- Abstract the results into higher layer by using pooling
- Fine tune with fully-connected NN
https://goo.gl/G7kBjI
https://goo.gl/Xswsbd
http://goo.gl/5OR5oH
CONVOLUTIONAL NN (CNN)
CNN FEATURES
41 / 39
Terry Taewoong Um (terry.t.um@gmail.com)
http://yosinski.com/deepvis
42
CNN ARCHITECTURES
Terry Taewoong Um (terry.t.um@gmail.com)
AlexNet (2012)
VGG (2014)
GoogLeNet (2014) ResNet (2014)
43
APPLICATIONS
Terry Taewoong Um (terry.t.um@gmail.com)
https://goo.gl/1SjmTp
A. Karpathy @ Bay area DL school 2016
https://docs.google.com/presentation/d/
1Q1CmVVnjVJM_9CDk3B8Y6MWCavZOti
KmOLQ0XB7s9Vg/edit
44
MASK RCNN
45
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Static
data
(e.g. image)
Sequence
data
(e.g. natural
language)
POPULAR DL METHODS
Explicit
density
Implicit
density
(try to generate
realistic samples)
RECURRENT NN (RNN)
𝑥
ℎ
RNN
(folded)
RNN
(unfolded)
• Vanishing / exploding gradient problem
• Recurrent Neural Network (RNN)
46 / 39
Terry Taewoong Um (terry.t.um@gmail.com)
LONG-SHORT TERM MEMORY (LSTM)
• Long-short term memory (LSTM)
LSTM
47 / 39
Terry Taewoong Um (terry.t.um@gmail.com)
[S. Hochreiter & J. Schmidhuber 1998]
RNN APPLICATIONS
Terry Taewoong Um (terry.t.um@gmail.com)
(Andrej Karpathy, http://karpathy.github.io/2015/05/21/rnn-effectiveness/)
49
RNN APPLICATIONS
Terry Taewoong Um (terry.t.um@gmail.com)
• Sequence generation
• Classification
Speech recognition, Sentence/document classification,
Video classification, Activity recognition, …
𝑥
ℎ
RNN APPLICATIONS
(Andrej Karpathy, http://karpathy.github.io/2015/05/21/rnn-effectiveness/)
RNN APPLICATIONS
• Machine translation with attention mechanism
https://research.googleblog.com/
2016/09/a-neural-network-for-
machine.html
Terry Taewoong Um (terry.t.um@gmail.com)
52
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Static
data
(e.g. image)
Sequence
data
(e.g. natural
language)
POPULAR DL METHODS
Explicit
density
Implicit
density
(try to generate
realistic samples)
Terry Taewoong Um (terry.t.um@gmail.com)
53
Task 2:
emotion estimation
Task 1:
person identification
TASK-SPECIFIC FEATURES
Terry Taewoong Um (terry.t.um@gmail.com)
54
- Labeled data are difficult to collect
- Is this a right way to obtain a good representation?
(Lack of generalizability / transferability)
WHY UNSUPERVISED LEARNING?
Task
Deep learning
(end-to-end)
* Feature
extraction included
Terry Taewoong Um (terry.t.um@gmail.com)
55
GOOD REPRESENTATION?
Good representation
GOOD & BAD REPRESENTATION
Bad representation
57
Terry Taewoong Um (terry.t.um@gmail.com)
• Attempt to learn a good representation without labels
• Unsupervised learning is far more difficult than supervised learning
• Turn unsupervised learning into supervised learning!
UNSUPERVISED LEARNING
58
Terry Taewoong Um (terry.t.um@gmail.com)
• Objective : Minimize reconstruction error “오토엔코더의 모든것“,
https://www.slideshare.net/
NaverEngineering/ss-
96581209
AUTOENCODER
59
“All about VAE”, H. Lee, https://www.slideshare.net/NaverEngineering/ss-96581209
VARIATIONAL AUTOENCODER (VAE)
• Objective : Minimize reconstruction error + regularization loss
60
Terry Taewoong Um (terry.t.um@gmail.com)
OVERFITTING & REGULARIZATION
• Objective : Minimize reconstruction error + regularization loss
61
Terry Taewoong Um (terry.t.um@gmail.com)
http://blog.fastforwardlabs.com/2016/08/12/introdu
cing-variational-autoencoders-in-prose-and.html
VARIATIONAL AUTOENCODER (VAE)
Terry Taewoong Um (terry.t.um@gmail.com)
62
GENERATED IMAGES BY VAE
https://github.com/davidsandberg/facenet/wiki/Variational-autoencoder
Terry Taewoong Um (terry.t.um@gmail.com)
63
GENERATED IMAGES BY VAE
https://github.com/davidsandberg/facenet/wiki/Variational-autoencoder
64 / 39
Terry Taewoong Um (terry.t.um@gmail.com)
[X. Yan et al. 2016]
CONDITIONAL VAE
65 / 39
Terry Taewoong Um (terry.t.um@gmail.com)
[X. Yan et al. 2016]
Terry Taewoong Um (terry.t.um@gmail.com)
66
MUSIC VAE
67
Terry Taewoong Um (terry.t.um@gmail.com)
Generative
Adversarial
Network (GAN)
Variational
Autoencoder
(VAE)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Static
data
(e.g. image)
Sequence
data
(e.g. natural
language)
POPULAR DL METHODS
Explicit
density
Implicit
density
(try to generate
realistic samples)
68
GENERATIVE MODELS
이활석, “그림 그리는 AI”,
https://www.slideshare.net/NaverEngineering/ai-83896428
69
NOT OPTIMIZATION, BUT GAME
이활석, “그림 그리는 AI”,
https://www.slideshare.net/NaverEngineering/ai-83896428
http://bzit.donga.com/List/3/all/50/1202090/1
70 / 39
Terry Taewoong Um (terry.t.um@gmail.com)
DCGAN EBGAN LSGAN
WGAN BEGAN DRAGAN
GAN
SAMPLES FROM GAN
71
CYCLE-GAN
72
Terry Taewoong Um (terry.t.um@gmail.com)
CYCLE-GAN
73
Terry Taewoong Um (terry.t.um@gmail.com)
GAN VARIANTS
74 / 39
GAN zoo,
https://deephunt.in/the-
gan-zoo-79597dc8c347
Most of them have
been developed for
the last year
Terry Taewoong Um (terry.t.um@gmail.com)
VOICE GENERATION ( A U TOR EGR ESSIVE)
75
김태훈 (OpenAI), 네이버 Deview2017 “책읽는 딥러닝”
https://www.youtube.com/watch?v=klnfWhPGPRs&t=1992s
Terry Taewoong Um (terry.t.um@gmail.com)
76
Google Duplex
https://www.youtube.com/watch?v=D5VN56jQMWM&t=2m47s
RECOGNITION + GENERATION
77
POPULAR METHODS
Terry Taewoong Um (terry.t.um@gmail.com)
Variational
Autoencoder
(VAE)
Generative
Adversarial
Network (GAN)
Unsupervised learningSupervised learning
Convolutional
Neural Network
(CNN)
Recurrent
Neural Network
(RNN*)
* RNN can be used as unsupervised manner
Static
data
(e.g. image)
Sequence
data
(e.g. natural
language)
Explicit
density
Implicit
density
(try to generate
realistic samples)
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
78
1. Introduction to ML & DL 50min
2. DL methods: CNN, RNN, VAE, GAN 35min
3. Can we believe DNNs? 15min
4. Q & A 15min
Break 10min
Terry Taewoong Um (terry.t.um@gmail.com)
BELIEVE OR NOT
79
green?
enemy?
1. Adversarial attacks
2. Uncertainty
3. Interpretability
Terry Taewoong Um (terry.t.um@gmail.com)
BELIEVE OR NOT
80
[Keyword]
= NOISE
(perturbation)
1. Adversarial attacks
2. Uncertainty
3. Interpretability
81
Terry Taewoong Um (terry.t.um@gmail.com)
[Wang &
Bovik, 2002]
ERRORS IN INPUT SPACE
Terry Taewoong Um (terry.t.um@gmail.com)
ADVERSARIAL ATTACKS
82
Gradient ascent method:
Increase “the changes of the loss” w.r.t. the changes of the input”
Terry Taewoong Um (terry.t.um@gmail.com)
83
ADVERSARIAL ATTACKS
• Adversarial examples in the physical world (Kurakin et al. 2016)
Terry Taewoong Um (terry.t.um@gmail.com)
ADVERSARIAL ATTACKS
84
• Adversarial patch (Brown et al. 2017)
Terry Taewoong Um (terry.t.um@gmail.com)
ADVERSARIAL TRAINING
85
https://www.spsc.tugraz.at/research/roM/virtual-adversarial-training-
applied-neural-higher-order-factors-phone-classification
• Virtual adversarial training (Miyato et al. 2016)
https://youtu.be/kvPmArtVoFE
Terry Taewoong Um (terry.t.um@gmail.com)
BELIEVE OR NOT
86
green?
enemy?
1. Adversarial attacks
2. Uncertainty
3. Interpretability
Terry Taewoong Um (terry.t.um@gmail.com)
BAYESIAN APPROACHES
87
https://youtu.be/kvPmArtVoFE
• Posterior ∝ Prior * Likelihood
Terry Taewoong Um (terry.t.um@gmail.com)
GAUSSIAN PROCESS
88
https://youtu.be/kvPmArtVoFE
Beautiful, but not scalable!
Terry Taewoong Um (terry.t.um@gmail.com)
DROPOUT AS BAYESIAN
89
• Dropout: Randomly drop nodes
→ regularization
Terry Taewoong Um (terry.t.um@gmail.com)
BELIEVE OR NOT
90
green?
enemy?
1. Adversarial attacks
2. Uncertainty
3. Interpretability
OCCLUSION TEST
Terry Taewoong Um (terry.t.um@gmail.com)
CLASS ACTIVATION MAP (CAM)
• Detect the most discriminative
parts from the label (without
the need of bounding boxes)
CAM
Terry Taewoong Um (terry.t.um@gmail.com)
93
Terry Taewoong Um (terry.t.um@gmail.com)
AI FOR ETHICS?
94
green?
enemy?
1. Adversarial attacks
2. Uncertainty
3. Interpretability
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
95
1. Introduction & ML basics 35min
2. Supervised Learning: CNN & RNN 20min
3. Unsupervised Learning: VAE & GAN 20min
4. Can we believe DNNs? 15min
5. Q & A 15min
Break 10min

More Related Content

What's hot

What's hot (20)

Data Science, Machine Learning and Neural Networks
Data Science, Machine Learning and Neural NetworksData Science, Machine Learning and Neural Networks
Data Science, Machine Learning and Neural Networks
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Tensorflow presentation
Tensorflow presentationTensorflow presentation
Tensorflow presentation
 
Recurrent neural networks rnn
Recurrent neural networks   rnnRecurrent neural networks   rnn
Recurrent neural networks rnn
 
Scikit Learn intro
Scikit Learn introScikit Learn intro
Scikit Learn intro
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learning
 
End-to-End Object Detection with Transformers
End-to-End Object Detection with TransformersEnd-to-End Object Detection with Transformers
End-to-End Object Detection with Transformers
 
Intepretability / Explainable AI for Deep Neural Networks
Intepretability / Explainable AI for Deep Neural NetworksIntepretability / Explainable AI for Deep Neural Networks
Intepretability / Explainable AI for Deep Neural Networks
 
Object Detection with Transformers
Object Detection with TransformersObject Detection with Transformers
Object Detection with Transformers
 
Lessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsLessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systems
 
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
 
Transformers In Vision From Zero to Hero (DLI).pptx
Transformers In Vision From Zero to Hero (DLI).pptxTransformers In Vision From Zero to Hero (DLI).pptx
Transformers In Vision From Zero to Hero (DLI).pptx
 
lecun-01.ppt
lecun-01.pptlecun-01.ppt
lecun-01.ppt
 
Transfer Learning: An overview
Transfer Learning: An overviewTransfer Learning: An overview
Transfer Learning: An overview
 
Deep learning
Deep learningDeep learning
Deep learning
 
Faster R-CNN - PR012
Faster R-CNN - PR012Faster R-CNN - PR012
Faster R-CNN - PR012
 
Moving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNNMoving Object Detection And Tracking Using CNN
Moving Object Detection And Tracking Using CNN
 
Reinforcement learning
Reinforcement learningReinforcement learning
Reinforcement learning
 
ViT.pptx
ViT.pptxViT.pptx
ViT.pptx
 
Object detection - RCNNs vs Retinanet
Object detection - RCNNs vs RetinanetObject detection - RCNNs vs Retinanet
Object detection - RCNNs vs Retinanet
 

Similar to Deep learning (Machine learning) tutorial for beginners

A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013
Philip Zheng
 
01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk
JesusTekonbo
 
Machine Learning and Inductive Inference
Machine Learning and Inductive InferenceMachine Learning and Inductive Inference
Machine Learning and Inductive Inference
butest
 
A NEAT Way for Evolving Echo State Networks
A NEAT Way for Evolving Echo State NetworksA NEAT Way for Evolving Echo State Networks
A NEAT Way for Evolving Echo State Networks
Kyriakos Chatzidimitriou
 
9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf
9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf
9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf
AmirMohamedNabilSale
 

Similar to Deep learning (Machine learning) tutorial for beginners (20)

Introduction to Machine Learning and Deep Learning
Introduction to Machine Learning and Deep LearningIntroduction to Machine Learning and Deep Learning
Introduction to Machine Learning and Deep Learning
 
Introduction to Deep Learning with TensorFlow
Introduction to Deep Learning with TensorFlowIntroduction to Deep Learning with TensorFlow
Introduction to Deep Learning with TensorFlow
 
Learning with side information through modality hallucination (2016)
Learning with side information through modality hallucination (2016)Learning with side information through modality hallucination (2016)
Learning with side information through modality hallucination (2016)
 
기계학습(Machine learning) 입문하기
기계학습(Machine learning) 입문하기기계학습(Machine learning) 입문하기
기계학습(Machine learning) 입문하기
 
01_introduction_ML.pdf
01_introduction_ML.pdf01_introduction_ML.pdf
01_introduction_ML.pdf
 
deepnet-lourentzou.ppt
deepnet-lourentzou.pptdeepnet-lourentzou.ppt
deepnet-lourentzou.ppt
 
A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
 
Language translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowLanguage translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlow
 
01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk
 
cs330_2021_lifelong_learning.pdf
cs330_2021_lifelong_learning.pdfcs330_2021_lifelong_learning.pdf
cs330_2021_lifelong_learning.pdf
 
Machine Learning and Inductive Inference
Machine Learning and Inductive InferenceMachine Learning and Inductive Inference
Machine Learning and Inductive Inference
 
Machine learning-in-details-with-out-python-code
Machine learning-in-details-with-out-python-codeMachine learning-in-details-with-out-python-code
Machine learning-in-details-with-out-python-code
 
A NEAT Way for Evolving Echo State Networks
A NEAT Way for Evolving Echo State NetworksA NEAT Way for Evolving Echo State Networks
A NEAT Way for Evolving Echo State Networks
 
Interaction Networks for Learning about Objects, Relations and Physics
Interaction Networks for Learning about Objects, Relations and PhysicsInteraction Networks for Learning about Objects, Relations and Physics
Interaction Networks for Learning about Objects, Relations and Physics
 
know Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfknow Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdf
 
Machine learning
Machine learningMachine learning
Machine learning
 
9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf
9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf
9.b-CMPS 403-F20-Session 9-Intro to ML II.pdf
 
Machine Learning: A gentle Introduction
Machine Learning: A gentle IntroductionMachine Learning: A gentle Introduction
Machine Learning: A gentle Introduction
 

More from Terry Taewoong Um

More from Terry Taewoong Um (14)

#44. KAIST에서 "대학 유죄"를 외치다: ART Lab의 도전
#44. KAIST에서 "대학 유죄"를 외치다: ART Lab의 도전#44. KAIST에서 "대학 유죄"를 외치다: ART Lab의 도전
#44. KAIST에서 "대학 유죄"를 외치다: ART Lab의 도전
 
A brief introduction to OCR (Optical character recognition)
A brief introduction to OCR (Optical character recognition)A brief introduction to OCR (Optical character recognition)
A brief introduction to OCR (Optical character recognition)
 
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynami...
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynami...Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynami...
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynami...
 
인공지능의 사회정의의 편이 될 수 있을까? (인공지능과 법)
인공지능의 사회정의의 편이 될 수 있을까? (인공지능과 법)인공지능의 사회정의의 편이 될 수 있을까? (인공지능과 법)
인공지능의 사회정의의 편이 될 수 있을까? (인공지능과 법)
 
Deep Variational Bayes Filters (2017)
Deep Variational Bayes Filters (2017)Deep Variational Bayes Filters (2017)
Deep Variational Bayes Filters (2017)
 
On Calibration of Modern Neural Networks (2017)
On Calibration of Modern Neural Networks (2017)On Calibration of Modern Neural Networks (2017)
On Calibration of Modern Neural Networks (2017)
 
Deep Learning: A Critical Appraisal (2018)
Deep Learning: A Critical Appraisal (2018)Deep Learning: A Critical Appraisal (2018)
Deep Learning: A Critical Appraisal (2018)
 
Understanding Black-box Predictions via Influence Functions (2017)
Understanding Black-box Predictions via Influence Functions (2017)Understanding Black-box Predictions via Influence Functions (2017)
Understanding Black-box Predictions via Influence Functions (2017)
 
Human Motion Forecasting (Generation) with RNNs
Human Motion Forecasting (Generation) with RNNsHuman Motion Forecasting (Generation) with RNNs
Human Motion Forecasting (Generation) with RNNs
 
Deformable Convolutional Network (2017)
Deformable Convolutional Network (2017)Deformable Convolutional Network (2017)
Deformable Convolutional Network (2017)
 
About Two Motion Planning Papers
About Two Motion Planning PapersAbout Two Motion Planning Papers
About Two Motion Planning Papers
 
Lie Group Formulation for Robot Mechanics
Lie Group Formulation for Robot MechanicsLie Group Formulation for Robot Mechanics
Lie Group Formulation for Robot Mechanics
 
로봇과 인공지능, 그리고 미래의 노동
로봇과 인공지능, 그리고 미래의 노동로봇과 인공지능, 그리고 미래의 노동
로봇과 인공지능, 그리고 미래의 노동
 
Lie Group Formulation for Robot Mechanics
Lie Group Formulation for Robot MechanicsLie Group Formulation for Robot Mechanics
Lie Group Formulation for Robot Mechanics
 

Recently uploaded

Automobile Management System Project Report.pdf
Automobile Management System Project Report.pdfAutomobile Management System Project Report.pdf
Automobile Management System Project Report.pdf
Kamal Acharya
 
Digital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdfDigital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdf
AbrahamGadissa
 
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdfONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
Kamal Acharya
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
Kamal Acharya
 
Online blood donation management system project.pdf
Online blood donation management system project.pdfOnline blood donation management system project.pdf
Online blood donation management system project.pdf
Kamal Acharya
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
Atif Razi
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
Kamal Acharya
 

Recently uploaded (20)

The Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfThe Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdf
 
Automobile Management System Project Report.pdf
Automobile Management System Project Report.pdfAutomobile Management System Project Report.pdf
Automobile Management System Project Report.pdf
 
Digital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdfDigital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdf
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
 
A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdf
A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdfA CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdf
A CASE STUDY ON ONLINE TICKET BOOKING SYSTEM PROJECT.pdf
 
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdfONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
ONLINE VEHICLE RENTAL SYSTEM PROJECT REPORT.pdf
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdf
 
Online blood donation management system project.pdf
Online blood donation management system project.pdfOnline blood donation management system project.pdf
Online blood donation management system project.pdf
 
Toll tax management system project report..pdf
Toll tax management system project report..pdfToll tax management system project report..pdf
Toll tax management system project report..pdf
 
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical EngineeringIntroduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
 
The Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docx
The Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docxThe Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docx
The Ultimate Guide to External Floating Roofs for Oil Storage Tanks.docx
 
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data StreamKIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
KIT-601 Lecture Notes-UNIT-3.pdf Mining Data Stream
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdf
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
 
Halogenation process of chemical process industries
Halogenation process of chemical process industriesHalogenation process of chemical process industries
Halogenation process of chemical process industries
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
 
Courier management system project report.pdf
Courier management system project report.pdfCourier management system project report.pdf
Courier management system project report.pdf
 
Furniture showroom management system project.pdf
Furniture showroom management system project.pdfFurniture showroom management system project.pdf
Furniture showroom management system project.pdf
 

Deep learning (Machine learning) tutorial for beginners

  • 1. Terry Taewoong Um (terry.t.um@gmail.com) University of Waterloo Department of Electrical & Computer Engineering Terry Taewoong Um DEEP LEARNING TUTORIAL IN 100 MINS 1
  • 2. Terry Taewoong Um (terry.t.um@gmail.com) WHO AM I 2 2008 – 2010 M.S. at Seoul National University, Korea c.f. “Tangent Space RRT with Lazy Projection: An Efficient Planning Algorithm for Constrained Motions”, T. T. Um et al., ARK2010. 2010 – 2014 Robotics researcher at LIG Nex1 / KIST, Korea c.f. “Independent Joint Learning: A Novel Task-to-Task Transfer Learning Scheme for Robot Models”, T. T. Um et al., ICRA2014. • I am a robotics researcher
  • 3. Terry Taewoong Um (terry.t.um@gmail.com) WHO AM I 3 2014 – Present PhD candidate at U.Waterloo, Canada c.f. “Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks”, T. T. Um et al., IROS2017. • I am a deep learning researcher http://hookedoneverything.com/parkinsons/ https://www.trainwithpush.com/ PUSH project Parkinson’s disease (PD) project
  • 4. WHO AM I 4 • But I am more known for ... - Facebook communities : 로봇공학을 위한 열린 모임, Tensorflow Korea, etc. - Blog / Youtube : 테리의 딥러닝 토크, T-Robotics, 대학원생 때 알았더라면 좋았을 이야기들 - Etc. : Most-cited DL papers (github)
  • 5. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 5 1. Introduction to ML & DL 50min 2. DL methods: CNN, RNN, VAE, GAN 35min 3. Can we believe DNNs? 15min 4. Q & A 15min Break 10min
  • 6. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 6 1. Introduction to ML & DL 50min 2. DL methods: CNN, RNN, VAE, GAN 35min 3. Can we believe DNNs? 15min 4. Q & A 15min Break 10min
  • 7. 7 Terry Taewoong Um (terry.t.um@gmail.com) https://github.com/sjchoi86/ dl_tutorials_10weeks https://github.com/terryum/ awesome-deep-learning-papers http://videolectures.net/ deeplearning2017_montreal/ • Deep learning summer school STUDY MATERIALS • Andrew Ng, Deeplearning.ai / Coursera • Stanford Univ., CS231n (CNNs) / CS224d (RNNs) • Various tutorials presented in NIPS, ICML, etc.
  • 8. Terry Taewoong Um (terry.t.um@gmail.com) 8 AI, ML, DL, NN https://medium.com/zeroth-ai/understanding- artificial-intelligence-b9b58f9b25c2
  • 9. Terry Taewoong Um (terry.t.um@gmail.com) 9 RECOGNITION - IMAGE Google photos Object recognition (image retrieval)
  • 10. Terry Taewoong Um (terry.t.um@gmail.com) 10 YOLO v2, https://www.youtube.com/watch?v=VOC3huqHrss RECOGNITION - IMAGE Object detection
  • 11. Terry Taewoong Um (terry.t.um@gmail.com) 11 RECOGNITION - NATURAL LANGUAGE Sentiment classification SAD Joyful
  • 12. Terry Taewoong Um (terry.t.um@gmail.com) 12 Speech recognition RECOGNITION - SPEECH
  • 13. PUSH Inc., https://youtu.be/JpzuVPesFLY Terry Taewoong Um (terry.t.um@gmail.com) 13 RECOGNITION - WEARABLES Exercise recognition Parkinson’s disease assessment
  • 14. Terry Taewoong Um (terry.t.um@gmail.com) 14 SUPERVISED LEARNING Train : X → Y image, text, speech, wearable data, etc. labels Test : X → ? (real practice) * Never use the test dataset during the development of a model (training)
  • 16. Terry Taewoong Um (terry.t.um@gmail.com) 16 OVERFITTING good performance for training data bad performance for test data model complexity error training error test error • Model complexity vs. Error
  • 17. Terry Taewoong Um (terry.t.um@gmail.com) 17 SUPERVISED LEARNING Train : X → Y image, text, speech, wearable data, etc. labels Test : X → ? (real practice) * Never use the test dataset during the development of a model (training)
  • 18. Terry Taewoong Um (terry.t.um@gmail.com) 18 VALIDATION SET Train : X → Y image, text, speech, wearable data, etc. labels Validation : X → ? (real-practice indicator) Test : X → ? (real practice)
  • 19. Terry Taewoong Um (terry.t.um@gmail.com) 19 PREVENTING OVERFITTING training time error training error test error we should stop here training set validation set test set for training (parameter optimization) for early stopping (avoid overfitting) for evaluation (measure the performance) keep watching the validation error • Training / Validation / Test datasets
  • 20. Terry Taewoong Um (terry.t.um@gmail.com) 20 PREVENTING OVERFITTING training validation test • N-fold cross validation
  • 21. Terry Taewoong Um (terry.t.um@gmail.com) 21 BOLTS & NUTS OF BUILDING DL http://www.computervisionblog.com/2016/12/ nuts-and-bolts-of-building-deep.html Andrew Ng at NIPS2016
  • 22. Terry Taewoong Um (terry.t.um@gmail.com) 22 REGULARIZATION 𝑚𝑖𝑛𝑖𝑚𝑖𝑧𝑒 σ ||𝑦 − 𝑓(𝑥)||2 , where, 𝑓 𝑥 = 𝑤0 + 𝑤1 𝑥1 + 𝑤2 𝑥2 + ⋯ = 𝑊𝑋 𝑚𝑖𝑛𝑖𝑚𝑖𝑧𝑒 ෍ ||𝑦 − 𝑓(𝑥)||2 + ||𝑊|| 𝑚 (minimize error & prefer a simpler model)
  • 23. Terry Taewoong Um (terry.t.um@gmail.com) 23 GENERAL PROCEDURE OF ML Task Representation (Features) Feature extraction Machine learning IMAGE SPEECH Feature engineering
  • 24. Terry Taewoong Um (terry.t.um@gmail.com) 24 WHAT ARE THE GOOD FEATURES? http://twistedsifter.com/2016/03/puppy-or-bagel-meme-gallery/
  • 25. Terry Taewoong Um (terry.t.um@gmail.com) 25 GENERAL PROCEDURE OF DL Task Representation (Features) Feature extraction Machine learning Task Deep learning (end-to-end) * Feature extraction included
  • 26. Terry Taewoong Um (terry.t.um@gmail.com) 26 DEEP LEARNING • What is Deep Learning (DL) ? - Learning methods which have deep (not shallow) architecture - It usually allows end-to-end learning - It automatically learn intermediate representation. Thus, it can be regarded as a representation learning - It often contains stacked “neural network”. Thus, Deep learning usually indicates “deep neural network” “Deep Gaussian Process” (2013) https://youtu.be/NwoGqYsQifg http://goo.gl/fxmmPE http://goo.gl/5Ry08S
  • 27. Terry Taewoong Um (terry.t.um@gmail.com) 27 BIOLOGICAL EVIDENCE Yann LeCun, https://goo.gl/VVQXJG • The vental pathway in the visual cortex has multiple stages • There exist a lot of intermediate representations
  • 28. Terry Taewoong Um (terry.t.um@gmail.com) 28 IMAGENET CHALLENGE (ILSVRC) http://image-net.org/challenges/talks/2016/ILSVRC2016_10_09_clsloc.pdf • 1000 classes, 1.4 million images • The first “large-scale” ML challenge • Labeled by Amazon Mechanical Turk (Fei-Fei Lee, Stanford Univ.) • Need large-scale data → ImageNet • Need a scalable method → DL • Need computation power → GPU • Convolutional Neural Networks (CNNs) AlexNet (2012), VGG (2014), GoogLeNet (2015), ResNet (2016), DenseNet (2017)...
  • 29. 29 NEURAL NETWORKS Terry Taewoong Um (terry.t.um@gmail.com) (H. Lalochelle, DLSS2017) • A large parametric model (like high-order polynomials) • Learn the parameters using gradient descent (GD) method • Local minima problem? → Stochastic GD (SGD) • Overfitting problem? → Large-scale data
  • 30. 30 NEURAL NETWORKS Terry Taewoong Um (terry.t.um@gmail.com) • Neural networks = Composition of functions Linear combination 𝑊𝑥 + 𝑏 Activation σ(𝑊𝑥 + 𝑏) (…repeat…) Linear combination 𝑊 σ 𝑊(… ) + 𝑏 + 𝑏 Output activation σ 𝑜𝑢𝑡 (… ) Forward pass Backward pass Calculate the loss Loss(𝑦𝑡𝑟𝑢𝑒, 𝑦 𝑝𝑟𝑒𝑑) Gradient of the loss Gradient of the activation Gradient of the weights (…repeat…) Update the weights (H. Lalochelle, DLSS2017) ReLU or tanh Softmax or Linear Optimization: SGD, RMSProb, or Adam cross-entropy or MSE
  • 31. Terry Taewoong Um (terry.t.um@gmail.com) 31 from keras.models import Sequential from keras.layers import Dense from keras.datasets import mnist (x_train, y_train), (x_test, y_test) = mnist.load_data() model = Sequential() model.add(Dense(units=64, activation='relu', input_dim=100)) model.add(Dense(units=10, activation='softmax’)) model.compile(loss='categorical_crossentropy', optimizer='sgd’) model.fit(x_train, y_train, epochs=5) NN IN KERAS
  • 32. • Recognition & Supervised learning • Model selection & Overfitting • Training set split & Cross validation • Regularization • Deep learning : End-to-end learning • Neural Network Basics Terry Taewoong Um (terry.t.um@gmail.com) SUMMARY – PART1
  • 33. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 33 1. Introduction to ML & DL 50min 2. DL methods: CNN, RNN, VAE, GAN 35min 3. Can we believe DNNs? 15min 4. Q & A 15min Break 10min
  • 34. 34 POPULAR DL METHODS Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN) Reinforcement learning Deep Q- Network (DQN) Actor-Critic Policy gradient Yuxi Li, “Deep reinforcement learning: Overview” https://arxiv.org/abs/1701.07274
  • 35. 35 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) Labels (O) Labels (X) (mostly) Discriminative model (mostly) Generative model * RNN can be used as unsupervised manner POPULAR DL METHODS
  • 36. 36 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Explicit density Implicit density (try to generate realistic samples) POPULAR DL METHODS
  • 37. 37 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Static data (e.g. image) Sequence data (e.g. natural language) The area that I am most familiar with POPULAR DL METHODS Explicit density Implicit density (try to generate realistic samples)
  • 38. 38 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Static data (e.g. image) Sequence data (e.g. natural language) POPULAR DL METHODS Explicit density Implicit density (try to generate realistic samples)
  • 39. CONVOLUTIONAL NN (CNN) Fully-connected layers Convolutional layers w h n 39 / 39 p × 𝑞 Terry Taewoong Um (terry.t.um@gmail.com) e.g.) (1k*1k) image * 1k nodes = 1 billion parameters [Fully-connected] (3*3) kernel size * 64 kernels = 576 parameters [Convolutional] https://github.com/vdumoulin /conv_arithmetic
  • 40. Terry Taewoong Um (terry.t.um@gmail.com) 40 • How can we deal with real images which is much bigger than MNIST digit images? - Use not fully-connected, but locally-connected NN - Use convolutions to get various feature maps - Abstract the results into higher layer by using pooling - Fine tune with fully-connected NN https://goo.gl/G7kBjI https://goo.gl/Xswsbd http://goo.gl/5OR5oH CONVOLUTIONAL NN (CNN)
  • 41. CNN FEATURES 41 / 39 Terry Taewoong Um (terry.t.um@gmail.com) http://yosinski.com/deepvis
  • 42. 42 CNN ARCHITECTURES Terry Taewoong Um (terry.t.um@gmail.com) AlexNet (2012) VGG (2014) GoogLeNet (2014) ResNet (2014)
  • 43. 43 APPLICATIONS Terry Taewoong Um (terry.t.um@gmail.com) https://goo.gl/1SjmTp A. Karpathy @ Bay area DL school 2016 https://docs.google.com/presentation/d/ 1Q1CmVVnjVJM_9CDk3B8Y6MWCavZOti KmOLQ0XB7s9Vg/edit
  • 45. 45 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Static data (e.g. image) Sequence data (e.g. natural language) POPULAR DL METHODS Explicit density Implicit density (try to generate realistic samples)
  • 46. RECURRENT NN (RNN) 𝑥 ℎ RNN (folded) RNN (unfolded) • Vanishing / exploding gradient problem • Recurrent Neural Network (RNN) 46 / 39 Terry Taewoong Um (terry.t.um@gmail.com)
  • 47. LONG-SHORT TERM MEMORY (LSTM) • Long-short term memory (LSTM) LSTM 47 / 39 Terry Taewoong Um (terry.t.um@gmail.com) [S. Hochreiter & J. Schmidhuber 1998]
  • 48. RNN APPLICATIONS Terry Taewoong Um (terry.t.um@gmail.com) (Andrej Karpathy, http://karpathy.github.io/2015/05/21/rnn-effectiveness/)
  • 49. 49 RNN APPLICATIONS Terry Taewoong Um (terry.t.um@gmail.com) • Sequence generation • Classification Speech recognition, Sentence/document classification, Video classification, Activity recognition, … 𝑥 ℎ
  • 50. RNN APPLICATIONS (Andrej Karpathy, http://karpathy.github.io/2015/05/21/rnn-effectiveness/)
  • 51. RNN APPLICATIONS • Machine translation with attention mechanism https://research.googleblog.com/ 2016/09/a-neural-network-for- machine.html Terry Taewoong Um (terry.t.um@gmail.com)
  • 52. 52 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Static data (e.g. image) Sequence data (e.g. natural language) POPULAR DL METHODS Explicit density Implicit density (try to generate realistic samples)
  • 53. Terry Taewoong Um (terry.t.um@gmail.com) 53 Task 2: emotion estimation Task 1: person identification TASK-SPECIFIC FEATURES
  • 54. Terry Taewoong Um (terry.t.um@gmail.com) 54 - Labeled data are difficult to collect - Is this a right way to obtain a good representation? (Lack of generalizability / transferability) WHY UNSUPERVISED LEARNING? Task Deep learning (end-to-end) * Feature extraction included
  • 55. Terry Taewoong Um (terry.t.um@gmail.com) 55 GOOD REPRESENTATION?
  • 56. Good representation GOOD & BAD REPRESENTATION Bad representation
  • 57. 57 Terry Taewoong Um (terry.t.um@gmail.com) • Attempt to learn a good representation without labels • Unsupervised learning is far more difficult than supervised learning • Turn unsupervised learning into supervised learning! UNSUPERVISED LEARNING
  • 58. 58 Terry Taewoong Um (terry.t.um@gmail.com) • Objective : Minimize reconstruction error “오토엔코더의 모든것“, https://www.slideshare.net/ NaverEngineering/ss- 96581209 AUTOENCODER
  • 59. 59 “All about VAE”, H. Lee, https://www.slideshare.net/NaverEngineering/ss-96581209 VARIATIONAL AUTOENCODER (VAE) • Objective : Minimize reconstruction error + regularization loss
  • 60. 60 Terry Taewoong Um (terry.t.um@gmail.com) OVERFITTING & REGULARIZATION • Objective : Minimize reconstruction error + regularization loss
  • 61. 61 Terry Taewoong Um (terry.t.um@gmail.com) http://blog.fastforwardlabs.com/2016/08/12/introdu cing-variational-autoencoders-in-prose-and.html VARIATIONAL AUTOENCODER (VAE)
  • 62. Terry Taewoong Um (terry.t.um@gmail.com) 62 GENERATED IMAGES BY VAE https://github.com/davidsandberg/facenet/wiki/Variational-autoencoder
  • 63. Terry Taewoong Um (terry.t.um@gmail.com) 63 GENERATED IMAGES BY VAE https://github.com/davidsandberg/facenet/wiki/Variational-autoencoder
  • 64. 64 / 39 Terry Taewoong Um (terry.t.um@gmail.com) [X. Yan et al. 2016]
  • 65. CONDITIONAL VAE 65 / 39 Terry Taewoong Um (terry.t.um@gmail.com) [X. Yan et al. 2016]
  • 66. Terry Taewoong Um (terry.t.um@gmail.com) 66 MUSIC VAE
  • 67. 67 Terry Taewoong Um (terry.t.um@gmail.com) Generative Adversarial Network (GAN) Variational Autoencoder (VAE) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Static data (e.g. image) Sequence data (e.g. natural language) POPULAR DL METHODS Explicit density Implicit density (try to generate realistic samples)
  • 68. 68 GENERATIVE MODELS 이활석, “그림 그리는 AI”, https://www.slideshare.net/NaverEngineering/ai-83896428
  • 69. 69 NOT OPTIMIZATION, BUT GAME 이활석, “그림 그리는 AI”, https://www.slideshare.net/NaverEngineering/ai-83896428 http://bzit.donga.com/List/3/all/50/1202090/1
  • 70. 70 / 39 Terry Taewoong Um (terry.t.um@gmail.com) DCGAN EBGAN LSGAN WGAN BEGAN DRAGAN GAN
  • 72. CYCLE-GAN 72 Terry Taewoong Um (terry.t.um@gmail.com)
  • 73. CYCLE-GAN 73 Terry Taewoong Um (terry.t.um@gmail.com)
  • 74. GAN VARIANTS 74 / 39 GAN zoo, https://deephunt.in/the- gan-zoo-79597dc8c347 Most of them have been developed for the last year
  • 75. Terry Taewoong Um (terry.t.um@gmail.com) VOICE GENERATION ( A U TOR EGR ESSIVE) 75 김태훈 (OpenAI), 네이버 Deview2017 “책읽는 딥러닝” https://www.youtube.com/watch?v=klnfWhPGPRs&t=1992s
  • 76. Terry Taewoong Um (terry.t.um@gmail.com) 76 Google Duplex https://www.youtube.com/watch?v=D5VN56jQMWM&t=2m47s RECOGNITION + GENERATION
  • 77. 77 POPULAR METHODS Terry Taewoong Um (terry.t.um@gmail.com) Variational Autoencoder (VAE) Generative Adversarial Network (GAN) Unsupervised learningSupervised learning Convolutional Neural Network (CNN) Recurrent Neural Network (RNN*) * RNN can be used as unsupervised manner Static data (e.g. image) Sequence data (e.g. natural language) Explicit density Implicit density (try to generate realistic samples)
  • 78. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 78 1. Introduction to ML & DL 50min 2. DL methods: CNN, RNN, VAE, GAN 35min 3. Can we believe DNNs? 15min 4. Q & A 15min Break 10min
  • 79. Terry Taewoong Um (terry.t.um@gmail.com) BELIEVE OR NOT 79 green? enemy? 1. Adversarial attacks 2. Uncertainty 3. Interpretability
  • 80. Terry Taewoong Um (terry.t.um@gmail.com) BELIEVE OR NOT 80 [Keyword] = NOISE (perturbation) 1. Adversarial attacks 2. Uncertainty 3. Interpretability
  • 81. 81 Terry Taewoong Um (terry.t.um@gmail.com) [Wang & Bovik, 2002] ERRORS IN INPUT SPACE
  • 82. Terry Taewoong Um (terry.t.um@gmail.com) ADVERSARIAL ATTACKS 82 Gradient ascent method: Increase “the changes of the loss” w.r.t. the changes of the input”
  • 83. Terry Taewoong Um (terry.t.um@gmail.com) 83 ADVERSARIAL ATTACKS • Adversarial examples in the physical world (Kurakin et al. 2016)
  • 84. Terry Taewoong Um (terry.t.um@gmail.com) ADVERSARIAL ATTACKS 84 • Adversarial patch (Brown et al. 2017)
  • 85. Terry Taewoong Um (terry.t.um@gmail.com) ADVERSARIAL TRAINING 85 https://www.spsc.tugraz.at/research/roM/virtual-adversarial-training- applied-neural-higher-order-factors-phone-classification • Virtual adversarial training (Miyato et al. 2016) https://youtu.be/kvPmArtVoFE
  • 86. Terry Taewoong Um (terry.t.um@gmail.com) BELIEVE OR NOT 86 green? enemy? 1. Adversarial attacks 2. Uncertainty 3. Interpretability
  • 87. Terry Taewoong Um (terry.t.um@gmail.com) BAYESIAN APPROACHES 87 https://youtu.be/kvPmArtVoFE • Posterior ∝ Prior * Likelihood
  • 88. Terry Taewoong Um (terry.t.um@gmail.com) GAUSSIAN PROCESS 88 https://youtu.be/kvPmArtVoFE Beautiful, but not scalable!
  • 89. Terry Taewoong Um (terry.t.um@gmail.com) DROPOUT AS BAYESIAN 89 • Dropout: Randomly drop nodes → regularization
  • 90. Terry Taewoong Um (terry.t.um@gmail.com) BELIEVE OR NOT 90 green? enemy? 1. Adversarial attacks 2. Uncertainty 3. Interpretability
  • 91. OCCLUSION TEST Terry Taewoong Um (terry.t.um@gmail.com)
  • 92. CLASS ACTIVATION MAP (CAM) • Detect the most discriminative parts from the label (without the need of bounding boxes)
  • 93. CAM Terry Taewoong Um (terry.t.um@gmail.com) 93
  • 94. Terry Taewoong Um (terry.t.um@gmail.com) AI FOR ETHICS? 94 green? enemy? 1. Adversarial attacks 2. Uncertainty 3. Interpretability
  • 95. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 95 1. Introduction & ML basics 35min 2. Supervised Learning: CNN & RNN 20min 3. Unsupervised Learning: VAE & GAN 20min 4. Can we believe DNNs? 15min 5. Q & A 15min Break 10min