Grad-CP8309-CMF-F2018 CP8309/CP8315: Deep Learning in Computer Vision

with Prof. Kosta Derpanis (Ryerson University)

Course description. Computer Vision is broadly defined as the study of recovering useful properties of the world from one or more images.  In recent years, Deep Learning has emerged as a powerful tool for addressing computer vision tasks.  This course will cover a range of foundational topics at the intersection of Deep Learning and Computer Vision.

Contact information.
kosta[at]scs.ryerson[dot]ca

Homepage
www.scs.ryerson.ca/~kosta

Prerequisites. University-level courses on linear algebra, multivariable calculus, and probability

Required textbook. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning (available for free and legally or purchase)

Optional textbook.  Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong, Mathematics for Machine Learning, (preprint available for free and legally)

Lectures. Below is the tentative schedule of topics.  Links to slides will be made available after each lecture.

# TOPIC SLIDES
PDF    MOV
0
Introduction to Computer Vision PDF MOV
1
Machine Learning Crash Course
PDF MOV
2
Ethics in Machine Learning
PDF MOV
NEURAL NETWORK FOUNDATIONS
3
Multilayer Perceptron
PDF MOV
4
Convolutional Network (ConvNet)
PDF MOV
5
Backprop
PDF MOV
6
Introduction to PyTorch (version 0.4.1)
PDF MOV
SPATIAL MODELS
7
Object Recognition Architectures PDF MOV
8
Training Networks
PDF MOV
9
Transfer Learning PDF MOV
10
Object Detection PDF MOV
11
Pixel Labeling Tasks PDF MOV
12
Optical Flow
PDF MOV
13
Segmentation Aware Filtering
PDF MOV
VISUALIZATION
14
Understanding ConvNets
PDF MOV
15
Texture Synthesis
PDF MOV
16
Style Transfer
PDF MOV
SEQUENTIAL MODELS
17
Recurrent Neural Network (RNN)
PDF MOV
18
Long Short-Term Memory (LSTM)
PDF MOV
19
Bidirectional RNN
PDF MOV
20
Vision and Language
PDF MOV
21
Action Recognition
PDF MOV
GENERATIVE MODELS
22
PixelNN (PixelRNN and PixelCNN)
PDF MOV
23
Variational Autoencoder (VAE)
24
Invertible Density Models - Normalizing Flows
25
Generative Adversarial Network (GAN)
ADVERSARIAL EXAMPLES
26
Adversarial Examples
PDF MOV

Related courses.
     Ryerson University CPS843: Introduction to Computer Vision with Kosta Derpanis
     Stanford CS231N: Convolutional Neural Networks for Visual Recognition with Fei Fei Li, Justin Johnson and Serena Young
     EPFL EE-559: Deep Learning
with Francois Fleuret
 

Acknowledgements. While a great effort has been made to assemble an original set of lecture slides, the essence of the presentation of many of the slides rely on material prepared by the following people: Andrej Karpathy, Justin Johnson, Serena Young, Fei Fei Li, Francois Fleuret, Graham Taylor, Carl Doersch