Introduction to Deep Learning
|
|
- Damian Warren
- 5 years ago
- Views:
Transcription
1 Introduction to Deep Learning A. G. Schwing & S. Fidler University of Toronto, 2015 A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
2 Outline 1 Universality of Neural Networks 2 Learning Neural Networks 3 Deep Learning 4 Applications 5 References A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
3 What are neural networks? Let s ask Biological Input layer Hidden layer Output layer Input #1 Computational Input #2 Input #3 Input #4 Output A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
4 What are neural networks?...neural networks (NNs) are computational models inspired by biological neural networks [...] and are used to estimate or approximate functions... [Wikipedia] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
5 What are neural networks? Origins: Traced back to threshold logic [W. McCulloch and W. Pitts, 1943] Perceptron [F. Rosenblatt, 1958] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
6 What are neural networks? Use cases Classification Playing video games Captcha Neural Turing Machine (e.g., learn how to sort) Alex Graves A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
7 What are neural networks? Example: input x parameters w 1, w 2, b A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
8 What are neural networks? Example: input x parameters w 1, w 2, b x R w 1 w 2 h 1 f b R A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
9 How to compute the function? Forward propagation/pass, inference, prediction: Given input x and parameters w, b Compute (latent variables/) intermediate results in a feed-forward manner Until we obtain output function f x R w 1 w 2 h 1 f b R A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
10 How to compute the function? Forward propagation/pass, inference, prediction: Given input x and parameters w, b Compute (latent variables/) intermediate results in a feed-forward manner Until we obtain output function f A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
11 How to compute the function? Example: input x, parameters w 1, w 2, b x R w 1 w 2 h 1 f b R A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
12 How to compute the function? Example: input x, parameters w 1, w 2, b x R w 1 h w 2 1 f h 1 = σ(w 1 x + b) b R f = w 2 h 1 Sigmoid function: σ(z) = 1/(1 + exp( z)) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
13 How to compute the function? Example: input x, parameters w 1, w 2, b x R w 1 h w 2 1 f h 1 = σ(w 1 x + b) b R f = w 2 h 1 Sigmoid function: σ(z) = 1/(1 + exp( z)) x = ln 2, b = ln 3, w 1 = 2, w 2 = 2 h 1 =? f =? A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
14 How to compute the function? Given parameters, what is f for x = 0, x = 1, x = 2,... f = w 2 σ(w 1 x + b) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
15 f How to compute the function? Given parameters, what is f for x = 0, x = 1, x = 2,... f = w 2 σ(w 1 x + b) x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
16 Let s mess with parameters: x R w 1 h 1 w 2 f h 1 = σ(w 1 x + b) f = w 2 h 1 b R σ(z) = 1/(1 + exp( z)) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
17 Let s mess with parameters: x R w 1 h 1 w 2 f h 1 = σ(w 1 x + b) f = w 2 h 1 b R σ(z) = 1/(1 + exp( z)) w 1 = 1.0, b changes A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
18 Let s mess with parameters: f x R w 1 h 1 w 2 f h 1 = σ(w 1 x + b) f = w 2 h 1 b R σ(z) = 1/(1 + exp( z)) w 1 = 1.0, b changes 0.4 b = b = 0 b = x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
19 Let s mess with parameters: f x R w 1 h 1 w 2 f h 1 = σ(w 1 x + b) f = w 2 h 1 b R σ(z) = 1/(1 + exp( z)) 1 w 1 = 1.0, b changes b = 0, w 1 changes b = b = 0 b = x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
20 Let s mess with parameters: f x R w 1 h 1 w 2 f h 1 = σ(w 1 x + b) f = w 2 h 1 b R σ(z) = 1/(1 + exp( z)) w 1 = 1.0, b changes b = 0, w 1 changes b = b = 0 b = x 0.6 = 0 fw1 0.4 w 1 = w 1 = 1.0 w 1 = x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
21 Let s mess with parameters: f x R w 1 h 1 w 2 f h 1 = σ(w 1 x + b) f = w 2 h 1 b R σ(z) = 1/(1 + exp( z)) w 1 = 1.0, b changes b = 0, w 1 changes b = b = 0 b = x 0.6 = 0 fw1 0.4 w 1 = w 1 = 1.0 w 1 = x Keep in mind the step function. A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
22 How to use Neural Networks for binary classification? Feature/Measurement: x Output: How likely is the input to be a cat? y x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
23 f How to use Neural Networks for binary classification? Feature/Measurement: x Output: How likely is the input to be a cat? x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
24 f How to use Neural Networks for binary classification? Feature/Measurement: x Output: How likely is the input to be a cat? x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
25 f How to use Neural Networks for binary classification? Feature/Measurement: x Output: How likely is the input to be a cat? x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
26 f How to use Neural Networks for binary classification? Shifted feature/measurement: x Output: How likely is the input to be a cat? Previous features x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
27 f f How to use Neural Networks for binary classification? Shifted feature/measurement: x Output: How likely is the input to be a cat? Previous features x Shifted features x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
28 f f How to use Neural Networks for binary classification? Shifted feature/measurement: x Output: How likely is the input to be a cat? Previous features x Shifted features x Learning/Training means finding the right parameters. A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
29 f So far we are able to scale and translate sigmoids. How well can we approximate an arbitrary function? With the simple model we are obviously not going very far. Features are good Simple classifier x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
30 f f So far we are able to scale and translate sigmoids. How well can we approximate an arbitrary function? With the simple model we are obviously not going very far. Features are good Simple classifier Features are noisy More complex classifier x x A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
31 f f So far we are able to scale and translate sigmoids. How well can we approximate an arbitrary function? With the simple model we are obviously not going very far. Features are good Simple classifier Features are noisy More complex classifier x x How can we generalize? A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
32 Let s use more hidden variables: b 1 h 1 x R w 1 w 2 w 3 w 4 f h 1 = σ(w 1 x + b 1 ) h 2 = σ(w 3 x + b 2 ) f = w 2 h 1 + w 4 h 2 h 2 b 2 A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
33 Let s use more hidden variables: f b 1 h 1 x R w 1 w 2 w 3 w 4 f h 1 = σ(w 1 x + b 1 ) h 2 = σ(w 3 x + b 2 ) f = w 2 h 1 + w 4 h 2 h 2 b 2 Combining two step functions gives a bump x w 1 = 100, b 1 = 40, w 3 = 100, b 2 = 60, w 2 = 1, w 4 = 1 A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
34 So let s simplify: b 1 x R w 1 h 1 w 2 w 3 w 4 f h 2 b 2 Bump(x 1, x 2, h) f We simplify a pair of hidden nodes to a bump function: Starts at x 1 Ends at x 2 Has height h A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
35 Now we can represent bumps very well. How can we generalize? A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
36 Now we can represent bumps very well. How can we generalize? f Bump(0.0, 0.2, h 1 ) Bump(0.2, 0.4, h 2 ) Bump(0.4, 0.6, h 3 ) f Bump(0.6, 0.8, h 4 ) Bump(0.8, 1.0, h 5) Target Approximation x More bumps gives more accurate approximation. Corresponds to a single layer network. A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
37 Universality: theoretically we can approximate an arbitrary function So we can learn a really complex cat classifier Where is the catch? A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
38 Universality: theoretically we can approximate an arbitrary function So we can learn a really complex cat classifier Where is the catch? Complexity, we might need quite a few hidden units Overfitting, memorize the training data A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
39 Generalizations are possible to A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
40 Generalizations are possible to include more input dimensions capture more output dimensions employ multiple layers for more efficient representations See for a great read! A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
41 How do we find the parameters to obtain a good approximation? How do we tell a computer to do that? A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
42 How do we find the parameters to obtain a good approximation? How do we tell a computer to do that? Intuitive explanation: Compute approximation error at the output Propagate error back by computing individual contributions of parameters to error [Fig. from H. Lee] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
43 Example for backpropagation of error: Target function: 5x 2 Approximation: f (x, w) Domain of interest: x {0, 1, 2, 3} Error: e(w) = (5x 2 f (x, w)) 2 x {0,1,2,3} A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
44 Example for backpropagation of error: Target function: 5x 2 Approximation: f (x, w) Domain of interest: x {0, 1, 2, 3} Error: Program of interest: min w e(w) = e(w) = min w x {0,1,2,3} x {0,1,2,3} (5x 2 f (x, w)) 2 (5x 2 f (x, w)) 2 }{{} l(x,w) How to optimize? A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
45 Example for backpropagation of error: Target function: 5x 2 Approximation: f (x, w) Domain of interest: x {0, 1, 2, 3} Error: Program of interest: min w e(w) = e(w) = min w x {0,1,2,3} x {0,1,2,3} (5x 2 f (x, w)) 2 (5x 2 f (x, w)) 2 }{{} l(x,w) How to optimize? Gradient descent A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
46 Gradient descent min e(w) w A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
47 Gradient descent min e(w) w Algorithm: start with w 0, t = 0 1 Compute gradient g t = e 2 Update w t+1 = w t ηg t 3 Set t t + 1 w w=wt A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
48 Chain rule is important to compute gradients: min w e(w) = min w x {0,1,2,3} (5x 2 f (x, w)) 2 }{{} l(x,w) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
49 Chain rule is important to compute gradients: min w Loss function: l(x, w) e(w) = min w x {0,1,2,3} (5x 2 f (x, w)) 2 }{{} l(x,w) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
50 Chain rule is important to compute gradients: min w Loss function: l(x, w) Squared loss Log loss Hinge loss e(w) = min w x {0,1,2,3} (5x 2 f (x, w)) 2 }{{} l(x,w) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
51 Chain rule is important to compute gradients: min w Loss function: l(x, w) Squared loss Log loss Hinge loss Derivatives: e(w) = min w e(w) w = = x {0,1,2,3} x {0,1,2,3} (5x 2 f (x, w)) 2 }{{} l(x,w) l(x, w) w A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
52 Chain rule is important to compute gradients: min w Loss function: l(x, w) Squared loss Log loss Hinge loss Derivatives: e(w) = min w e(w) w = = x {0,1,2,3} x {0,1,2,3} x {0,1,2,3} (5x 2 f (x, w)) 2 }{{} l(x,w) l(x, w) w l(x, w) f (x, w) f w A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
53 Slightly more complex example: Composite function represented as a directed a-cyclic graph l(x, w) = f 1 (w 1, f 2 (w 2, f 3 (...))) f 1 (w 1, f 2 ) f f 1 1 w f 1 2 w 1 f 2 (w 2, f 3 ) f 1 f 2 f 2 f 3 f 1 f 2 f 2 w 2 w 2 f 3 (...) Repeated application of chain rule for efficient computation of all gradients A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
54 Back propagation doesn t work well for deep sigmoid networks: Diffusion of gradient signal (multiplication of many small numbers) Attractivity of many local minima (random initialization is very far from good points) Requires a lot of training samples Need for significant computational power A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
55 Back propagation doesn t work well for deep sigmoid networks: Diffusion of gradient signal (multiplication of many small numbers) Attractivity of many local minima (random initialization is very far from good points) Requires a lot of training samples Need for significant computational power Solution: 2 step approach Greedy layerwise pre-training Perform full fine tuning at the end A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
56 Why go deep? Representation efficiency (fewer computational units for the same function) Hierarchical representation (non-local generalization) Combinatorial sharing (re-use of earlier computation) Works very well [Fig. from H. Lee] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
57 To obtain more flexibility/non-linearity we use additional function prototypes: A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
58 To obtain more flexibility/non-linearity we use additional function prototypes: Sigmoid Rectified linear unit (ReLU) Pooling Dropout Convolutions A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
59 Convolutions What do the numbers mean? See Sanja s lecture 14 for the answers... [Fig. adapted from A. Krizhevsky] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
60 f conv (, ) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
61 f conv (, ) = A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
62 Max Pooling What is happening here? [Fig. adapted from A. Krizhevsky] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
63 A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
64 Rectified Linear Unit (ReLU) A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
65 Rectified Linear Unit (ReLU) Drop information if smaller than zero Fixes the problem of vanishing gradients to some degree A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
66 Rectified Linear Unit (ReLU) Drop information if smaller than zero Fixes the problem of vanishing gradients to some degree Dropout A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
67 Rectified Linear Unit (ReLU) Drop information if smaller than zero Fixes the problem of vanishing gradients to some degree Dropout Drop information at random Kind of a regularization, enforcing redundancy A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
68 A famous deep learning network called AlexNet. The network won the ImageNet competition in How many parameters? Given an image, what is happening? Inference Time: about 2ms per image when processing many images in parallel on the GPU Training Time: a few days given a single recent GPU [Fig. adapted from A. Krizhevsky] A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
69 Demo A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
70 Neural networks have been used for many applications: Classification and Recognition in Computer Vision Text Parsing in Natural Language Processing Playing Video Games Stock Market Prediction Captcha Demos: Russ website Antonio Places website A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
71 Classification in Computer Vision: ImageNet Challenge Since it s the end of the semester, let s find the beach... A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
72 Classification in Computer Vision: ImageNet Challenge A place to maybe prepare for exams... A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
73 Links: Tutorials: Toronto Demo by Russ and students: MIT Demo by Antonio and students: Honglak Lee: workshop-tutorial-final.pdf Yann LeCun: yann/talks/lecun-ranzato-icml2013.pdf Richard Socher: A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
74 Videos: Video games: Captcha: Stock exchange: A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding / 39
Introduction to Deep Learning
Introduction to Deep Learning A. G. Schwing & S. Fidler University of Toronto, 2014 A. G. Schwing & S. Fidler (UofT) CSC420: Intro to Image Understanding 2014 1 / 35 Outline 1 Universality of Neural Networks
More informationCSE446: Neural Networks Spring Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer
CSE446: Neural Networks Spring 2017 Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer Human Neurons Switching time ~ 0.001 second Number of neurons 10 10 Connections per neuron 10 4-5 Scene
More informationNeural Networks. Nicholas Ruozzi University of Texas at Dallas
Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify
More informationSGD and Deep Learning
SGD and Deep Learning Subgradients Lets make the gradient cheating more formal. Recall that the gradient is the slope of the tangent. f(w 1 )+rf(w 1 ) (w w 1 ) Non differentiable case? w 1 Subgradients
More informationLecture 17: Neural Networks and Deep Learning
UVA CS 6316 / CS 4501-004 Machine Learning Fall 2016 Lecture 17: Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions
More informationJakub Hajic Artificial Intelligence Seminar I
Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network
More informationAdministration. Registration Hw3 is out. Lecture Captioning (Extra-Credit) Scribing lectures. Questions. Due on Thursday 10/6
Administration Registration Hw3 is out Due on Thursday 10/6 Questions Lecture Captioning (Extra-Credit) Look at Piazza for details Scribing lectures With pay; come talk to me/send email. 1 Projects Projects
More informationNeural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications
Neural Networks Bishop PRML Ch. 5 Alireza Ghane Neural Networks Alireza Ghane / Greg Mori 1 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of
More informationClassification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses
More informationCSC 411 Lecture 10: Neural Networks
CSC 411 Lecture 10: Neural Networks Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 10-Neural Networks 1 / 35 Inspiration: The Brain Our brain has 10 11
More information(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann
(Feed-Forward) Neural Networks 2016-12-06 Dr. Hajira Jabeen, Prof. Jens Lehmann Outline In the previous lectures we have learned about tensors and factorization methods. RESCAL is a bilinear model for
More informationCSC321 Lecture 5: Multilayer Perceptrons
CSC321 Lecture 5: Multilayer Perceptrons Roger Grosse Roger Grosse CSC321 Lecture 5: Multilayer Perceptrons 1 / 21 Overview Recall the simple neuron-like unit: y output output bias i'th weight w 1 w2 w3
More informationNeural Networks and Deep Learning.
Neural Networks and Deep Learning www.cs.wisc.edu/~dpage/cs760/ 1 Goals for the lecture you should understand the following concepts perceptrons the perceptron training rule linear separability hidden
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
More informationIntroduction to Convolutional Neural Networks (CNNs)
Introduction to Convolutional Neural Networks (CNNs) nojunk@snu.ac.kr http://mipal.snu.ac.kr Department of Transdisciplinary Studies Seoul National University, Korea Jan. 2016 Many slides are from Fei-Fei
More informationArtificial Neural Networks. MGS Lecture 2
Artificial Neural Networks MGS 2018 - Lecture 2 OVERVIEW Biological Neural Networks Cell Topology: Input, Output, and Hidden Layers Functional description Cost functions Training ANNs Back-Propagation
More informationFrom perceptrons to word embeddings. Simon Šuster University of Groningen
From perceptrons to word embeddings Simon Šuster University of Groningen Outline A basic computational unit Weighting some input to produce an output: classification Perceptron Classify tweets Written
More informationNeural Networks. Intro to AI Bert Huang Virginia Tech
Neural Networks Intro to AI Bert Huang Virginia Tech Outline Biological inspiration for artificial neural networks Linear vs. nonlinear functions Learning with neural networks: back propagation https://en.wikipedia.org/wiki/neuron#/media/file:chemical_synapse_schema_cropped.jpg
More informationCSC321 Lecture 4: Learning a Classifier
CSC321 Lecture 4: Learning a Classifier Roger Grosse Roger Grosse CSC321 Lecture 4: Learning a Classifier 1 / 28 Overview Last time: binary classification, perceptron algorithm Limitations of the perceptron
More informationFeature Design. Feature Design. Feature Design. & Deep Learning
Artificial Intelligence and its applications Lecture 9 & Deep Learning Professor Daniel Yeung danyeung@ieee.org Dr. Patrick Chan patrickchan@ieee.org South China University of Technology, China Appropriately
More informationIntelligent Systems Discriminative Learning, Neural Networks
Intelligent Systems Discriminative Learning, Neural Networks Carsten Rother, Dmitrij Schlesinger WS2014/2015, Outline 1. Discriminative learning 2. Neurons and linear classifiers: 1) Perceptron-Algorithm
More informationA summary of Deep Learning without Poor Local Minima
A summary of Deep Learning without Poor Local Minima by Kenji Kawaguchi MIT oral presentation at NIPS 2016 Learning Supervised (or Predictive) learning Learn a mapping from inputs x to outputs y, given
More informationECE G: Special Topics in Signal Processing: Sparsity, Structure, and Inference
ECE 18-898G: Special Topics in Signal Processing: Sparsity, Structure, and Inference Neural Networks: A brief touch Yuejie Chi Department of Electrical and Computer Engineering Spring 2018 1/41 Outline
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
More informationNeural Networks: Introduction
Neural Networks: Introduction Machine Learning Fall 2017 Based on slides and material from Geoffrey Hinton, Richard Socher, Dan Roth, Yoav Goldberg, Shai Shalev-Shwartz and Shai Ben-David, and others 1
More informationCSC321 Lecture 4: Learning a Classifier
CSC321 Lecture 4: Learning a Classifier Roger Grosse Roger Grosse CSC321 Lecture 4: Learning a Classifier 1 / 31 Overview Last time: binary classification, perceptron algorithm Limitations of the perceptron
More informationARTIFICIAL INTELLIGENCE. Artificial Neural Networks
INFOB2KI 2017-2018 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Artificial Neural Networks Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html
More informationNeed for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels
Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)
More informationCSE 190 Fall 2015 Midterm DO NOT TURN THIS PAGE UNTIL YOU ARE TOLD TO START!!!!
CSE 190 Fall 2015 Midterm DO NOT TURN THIS PAGE UNTIL YOU ARE TOLD TO START!!!! November 18, 2015 THE EXAM IS CLOSED BOOK. Once the exam has started, SORRY, NO TALKING!!! No, you can t even say see ya
More informationCourse 395: Machine Learning - Lectures
Course 395: Machine Learning - Lectures Lecture 1-2: Concept Learning (M. Pantic) Lecture 3-4: Decision Trees & CBC Intro (M. Pantic & S. Petridis) Lecture 5-6: Evaluating Hypotheses (S. Petridis) Lecture
More informationUnderstanding How ConvNets See
Understanding How ConvNets See Slides from Andrej Karpathy Springerberg et al, Striving for Simplicity: The All Convolutional Net (ICLR 2015 workshops) CSC321: Intro to Machine Learning and Neural Networks,
More informationMachine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6
Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)
More informationNeural networks and optimization
Neural networks and optimization Nicolas Le Roux Criteo 18/05/15 Nicolas Le Roux (Criteo) Neural networks and optimization 18/05/15 1 / 85 1 Introduction 2 Deep networks 3 Optimization 4 Convolutional
More informationNeural Networks Lecturer: J. Matas Authors: J. Matas, B. Flach, O. Drbohlav
Neural Networks 30.11.2015 Lecturer: J. Matas Authors: J. Matas, B. Flach, O. Drbohlav 1 Talk Outline Perceptron Combining neurons to a network Neural network, processing input to an output Learning Cost
More informationReading Group on Deep Learning Session 1
Reading Group on Deep Learning Session 1 Stephane Lathuiliere & Pablo Mesejo 2 June 2016 1/31 Contents Introduction to Artificial Neural Networks to understand, and to be able to efficiently use, the popular
More informationIntroduction to Machine Learning
Introduction to Machine Learning Neural Networks Varun Chandola x x 5 Input Outline Contents February 2, 207 Extending Perceptrons 2 Multi Layered Perceptrons 2 2. Generalizing to Multiple Labels.................
More informationCS 179: LECTURE 16 MODEL COMPLEXITY, REGULARIZATION, AND CONVOLUTIONAL NETS
CS 179: LECTURE 16 MODEL COMPLEXITY, REGULARIZATION, AND CONVOLUTIONAL NETS LAST TIME Intro to cudnn Deep neural nets using cublas and cudnn TODAY Building a better model for image classification Overfitting
More informationFeed-forward Networks Network Training Error Backpropagation Applications. Neural Networks. Oliver Schulte - CMPT 726. Bishop PRML Ch.
Neural Networks Oliver Schulte - CMPT 726 Bishop PRML Ch. 5 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of biological plausibility We will
More informationArtificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen
Artificial Neural Networks Introduction to Computational Neuroscience Tambet Matiisen 2.04.2018 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition
More informationNeural Networks and Deep Learning
Neural Networks and Deep Learning Professor Ameet Talwalkar November 12, 2015 Professor Ameet Talwalkar Neural Networks and Deep Learning November 12, 2015 1 / 16 Outline 1 Review of last lecture AdaBoost
More information<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation)
Learning for Deep Neural Networks (Back-propagation) Outline Summary of Previous Standford Lecture Universal Approximation Theorem Inference vs Training Gradient Descent Back-Propagation
More informationNeural Networks. Learning and Computer Vision Prof. Olga Veksler CS9840. Lecture 10
CS9840 Learning and Computer Vision Prof. Olga Veksler Lecture 0 Neural Networks Many slides are from Andrew NG, Yann LeCun, Geoffry Hinton, Abin - Roozgard Outline Short Intro Perceptron ( layer NN) Multilayer
More informationLogistic Regression & Neural Networks
Logistic Regression & Neural Networks CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides credit: Graham Neubig, Jacob Eisenstein Logistic Regression Perceptron & Probabilities What if we want a probability
More informationCSC321 Lecture 16: ResNets and Attention
CSC321 Lecture 16: ResNets and Attention Roger Grosse Roger Grosse CSC321 Lecture 16: ResNets and Attention 1 / 24 Overview Two topics for today: Topic 1: Deep Residual Networks (ResNets) This is the state-of-the
More informationArtificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino
Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as
More informationy(x n, w) t n 2. (1)
Network training: Training a neural network involves determining the weight parameter vector w that minimizes a cost function. Given a training set comprising a set of input vector {x n }, n = 1,...N,
More informationNeural Networks (Part 1) Goals for the lecture
Neural Networks (Part ) Mark Craven and David Page Computer Sciences 760 Spring 208 www.biostat.wisc.edu/~craven/cs760/ Some of the slides in these lectures have been adapted/borrowed from materials developed
More informationMachine Learning for Signal Processing Neural Networks Continue. Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016
Machine Learning for Signal Processing Neural Networks Continue Instructor: Bhiksha Raj Slides by Najim Dehak 1 Dec 2016 1 So what are neural networks?? Voice signal N.Net Transcription Image N.Net Text
More informationECE521 Lecture 7/8. Logistic Regression
ECE521 Lecture 7/8 Logistic Regression Outline Logistic regression (Continue) A single neuron Learning neural networks Multi-class classification 2 Logistic regression The output of a logistic regression
More informationMachine Learning Lecture 12
Machine Learning Lecture 12 Neural Networks 30.11.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Course Outline Fundamentals Bayes Decision Theory Probability
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression
More informationLast update: October 26, Neural networks. CMSC 421: Section Dana Nau
Last update: October 26, 207 Neural networks CMSC 42: Section 8.7 Dana Nau Outline Applications of neural networks Brains Neural network units Perceptrons Multilayer perceptrons 2 Example Applications
More informationNeural networks. Chapter 19, Sections 1 5 1
Neural networks Chapter 19, Sections 1 5 Chapter 19, Sections 1 5 1 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 19, Sections 1 5 2 Brains 10
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)
More informationAN INTRODUCTION TO NEURAL NETWORKS. Scott Kuindersma November 12, 2009
AN INTRODUCTION TO NEURAL NETWORKS Scott Kuindersma November 12, 2009 SUPERVISED LEARNING We are given some training data: We must learn a function If y is discrete, we call it classification If it is
More informationMachine Learning for Physicists Lecture 1
Machine Learning for Physicists Lecture 1 Summer 2017 University of Erlangen-Nuremberg Florian Marquardt (Image generated by a net with 20 hidden layers) OUTPUT INPUT (Picture: Wikimedia Commons) OUTPUT
More informationMachine Learning Lecture 10
Machine Learning Lecture 10 Neural Networks 26.11.2018 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Today s Topic Deep Learning 2 Course Outline Fundamentals Bayes
More information1 What a Neural Network Computes
Neural Networks 1 What a Neural Network Computes To begin with, we will discuss fully connected feed-forward neural networks, also known as multilayer perceptrons. A feedforward neural network consists
More informationArtificial Neural Networks
Artificial Neural Networks Oliver Schulte - CMPT 310 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of biological plausibility We will focus on
More informationNeed for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels
Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)
More informationConvolutional Neural Networks. Srikumar Ramalingam
Convolutional Neural Networks Srikumar Ramalingam Reference Many of the slides are prepared using the following resources: neuralnetworksanddeeplearning.com (mainly Chapter 6) http://cs231n.github.io/convolutional-networks/
More informationNeural networks. Chapter 20. Chapter 20 1
Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms
More informationComments. Assignment 3 code released. Thought questions 3 due this week. Mini-project: hopefully you have started. implement classification algorithms
Neural networks Comments Assignment 3 code released implement classification algorithms use kernels for census dataset Thought questions 3 due this week Mini-project: hopefully you have started 2 Example:
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Neural networks Daniel Hennes 21.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Logistic regression Neural networks Perceptron
More informationDeep Learning: a gentle introduction
Deep Learning: a gentle introduction Jamal Atif jamal.atif@dauphine.fr PSL, Université Paris-Dauphine, LAMSADE February 8, 206 Jamal Atif (Université Paris-Dauphine) Deep Learning February 8, 206 / Why
More informationIntro to Neural Networks and Deep Learning
Intro to Neural Networks and Deep Learning Jack Lanchantin Dr. Yanjun Qi UVA CS 6316 1 Neurons 1-Layer Neural Network Multi-layer Neural Network Loss Functions Backpropagation Nonlinearity Functions NNs
More informationDeep Learning (CNNs)
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deep Learning (CNNs) Deep Learning Readings: Murphy 28 Bishop - - HTF - - Mitchell
More informationBackpropagation Introduction to Machine Learning. Matt Gormley Lecture 12 Feb 23, 2018
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Backpropagation Matt Gormley Lecture 12 Feb 23, 2018 1 Neural Networks Outline
More informationDEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY
DEEP LEARNING AND NEURAL NETWORKS: BACKGROUND AND HISTORY 1 On-line Resources http://neuralnetworksanddeeplearning.com/index.html Online book by Michael Nielsen http://matlabtricks.com/post-5/3x3-convolution-kernelswith-online-demo
More informationNeural Networks with Applications to Vision and Language. Feedforward Networks. Marco Kuhlmann
Neural Networks with Applications to Vision and Language Feedforward Networks Marco Kuhlmann Feedforward networks Linear separability x 2 x 2 0 1 0 1 0 0 x 1 1 0 x 1 linearly separable not linearly separable
More informationNeural networks. Chapter 20, Section 5 1
Neural networks Chapter 20, Section 5 Chapter 20, Section 5 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 20, Section 5 2 Brains 0 neurons of
More informationArtificial Neural Networks. Historical description
Artificial Neural Networks Historical description Victor G. Lopez 1 / 23 Artificial Neural Networks (ANN) An artificial neural network is a computational model that attempts to emulate the functions of
More informationNeural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA 1/ 21
Neural Networks Chapter 8, Section 7 TB Artificial Intelligence Slides from AIMA http://aima.cs.berkeley.edu / 2 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural
More informationCS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes
CS 6501: Deep Learning for Computer Graphics Basics of Neural Networks Connelly Barnes Overview Simple neural networks Perceptron Feedforward neural networks Multilayer perceptron and properties Autoencoders
More informationCSCI567 Machine Learning (Fall 2018)
CSCI567 Machine Learning (Fall 2018) Prof. Haipeng Luo U of Southern California Sep 12, 2018 September 12, 2018 1 / 49 Administration GitHub repos are setup (ask TA Chi Zhang for any issues) HW 1 is due
More informationIntroduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis
Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.
More informationCSC 411 Lecture 7: Linear Classification
CSC 411 Lecture 7: Linear Classification Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 07-Linear Classification 1 / 23 Overview Classification: predicting
More informationMachine Learning
Machine Learning 10-315 Maria Florina Balcan Machine Learning Department Carnegie Mellon University 03/29/2019 Today: Artificial neural networks Backpropagation Reading: Mitchell: Chapter 4 Bishop: Chapter
More informationNeural Networks: Backpropagation
Neural Networks: Backpropagation Machine Learning Fall 2017 Based on slides and material from Geoffrey Hinton, Richard Socher, Dan Roth, Yoav Goldberg, Shai Shalev-Shwartz and Shai Ben-David, and others
More informationNeural Networks. Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016
Neural Networks Yan Shao Department of Linguistics and Philology, Uppsala University 7 December 2016 Outline Part 1 Introduction Feedforward Neural Networks Stochastic Gradient Descent Computational Graph
More informationNeural Networks. David Rosenberg. July 26, New York University. David Rosenberg (New York University) DS-GA 1003 July 26, / 35
Neural Networks David Rosenberg New York University July 26, 2017 David Rosenberg (New York University) DS-GA 1003 July 26, 2017 1 / 35 Neural Networks Overview Objectives What are neural networks? How
More informationMachine Learning Basics III
Machine Learning Basics III Benjamin Roth CIS LMU München Benjamin Roth (CIS LMU München) Machine Learning Basics III 1 / 62 Outline 1 Classification Logistic Regression 2 Gradient Based Optimization Gradient
More informationNeural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /9/17
3/9/7 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/9/7 Perceptron as a neural
More informationSequence Modeling with Neural Networks
Sequence Modeling with Neural Networks Harini Suresh y 0 y 1 y 2 s 0 s 1 s 2... x 0 x 1 x 2 hat is a sequence? This morning I took the dog for a walk. sentence medical signals speech waveform Successes
More informationIntroduction to Neural Networks
CUONG TUAN NGUYEN SEIJI HOTTA MASAKI NAKAGAWA Tokyo University of Agriculture and Technology Copyright by Nguyen, Hotta and Nakagawa 1 Pattern classification Which category of an input? Example: Character
More informationLecture 4: Perceptrons and Multilayer Perceptrons
Lecture 4: Perceptrons and Multilayer Perceptrons Cognitive Systems II - Machine Learning SS 2005 Part I: Basic Approaches of Concept Learning Perceptrons, Artificial Neuronal Networks Lecture 4: Perceptrons
More informationCSC 411: Lecture 04: Logistic Regression
CSC 411: Lecture 04: Logistic Regression Raquel Urtasun & Rich Zemel University of Toronto Sep 23, 2015 Urtasun & Zemel (UofT) CSC 411: 04-Prob Classif Sep 23, 2015 1 / 16 Today Key Concepts: Logistic
More informationCSC 411: Lecture 02: Linear Regression
CSC 411: Lecture 02: Linear Regression Richard Zemel, Raquel Urtasun and Sanja Fidler University of Toronto (Most plots in this lecture are from Bishop s book) Zemel, Urtasun, Fidler (UofT) CSC 411: 02-Regression
More informationMultilayer Perceptrons and Backpropagation
Multilayer Perceptrons and Backpropagation Informatics 1 CG: Lecture 7 Chris Lucas School of Informatics University of Edinburgh January 31, 2017 (Slides adapted from Mirella Lapata s.) 1 / 33 Reading:
More informationSlide credit from Hung-Yi Lee & Richard Socher
Slide credit from Hung-Yi Lee & Richard Socher 1 Review Recurrent Neural Network 2 Recurrent Neural Network Idea: condition the neural network on all previous words and tie the weights at each time step
More informationFeedforward Neural Nets and Backpropagation
Feedforward Neural Nets and Backpropagation Julie Nutini University of British Columbia MLRG September 28 th, 2016 1 / 23 Supervised Learning Roadmap Supervised Learning: Assume that we are given the features
More informationCS489/698: Intro to ML
CS489/698: Intro to ML Lecture 03: Multi-layer Perceptron Outline Failure of Perceptron Neural Network Backpropagation Universal Approximator 2 Outline Failure of Perceptron Neural Network Backpropagation
More informationNonlinear Classification
Nonlinear Classification INFO-4604, Applied Machine Learning University of Colorado Boulder October 5-10, 2017 Prof. Michael Paul Linear Classification Most classifiers we ve seen use linear functions
More informationApprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning
Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire
More informationNatural Language Processing
Natural Language Processing Info 59/259 Lecture 4: Text classification 3 (Sept 5, 207) David Bamman, UC Berkeley . https://www.forbes.com/sites/kevinmurnane/206/04/0/what-is-deep-learning-and-how-is-it-useful
More informationIntroduction to (Convolutional) Neural Networks
Introduction to (Convolutional) Neural Networks Philipp Grohs Summer School DL and Vis, Sept 2018 Syllabus 1 Motivation and Definition 2 Universal Approximation 3 Backpropagation 4 Stochastic Gradient
More informationCS 1674: Intro to Computer Vision. Final Review. Prof. Adriana Kovashka University of Pittsburgh December 7, 2016
CS 1674: Intro to Computer Vision Final Review Prof. Adriana Kovashka University of Pittsburgh December 7, 2016 Final info Format: multiple-choice, true/false, fill in the blank, short answers, apply an
More informationNeural networks COMS 4771
Neural networks COMS 4771 1. Logistic regression Logistic regression Suppose X = R d and Y = {0, 1}. A logistic regression model is a statistical model where the conditional probability function has a
More informationConvolutional Neural Networks II. Slides from Dr. Vlad Morariu
Convolutional Neural Networks II Slides from Dr. Vlad Morariu 1 Optimization Example of optimization progress while training a neural network. (Loss over mini-batches goes down over time.) 2 Learning rate
More information