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.

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

Lectures.

#	TOPIC	SLIDES
0	Introduction to Computer Vision	PDF MOV
1	Ethics, Privacy and Security in Machine Learning	PDF MOV
2	Machine Learning Crash Course	PDF MOV
	NEURAL NETWORK FOUNDATIONS
3	Multilayer Perceptron	PDF MOV
4	Convolutional Network (ConvNet)	PDF MOV
5	Backprop	PDF MOV
6	Optimization	PDF MOV
7	Introduction to PyTorch (version 1.0+)	PDF MOV
9	Training Networks	PDF MOV
10	Weight Initialization	PDF MOV
11	Transfer Learning	PDF MOV
12	Teacher-Student Learning	PDF MOV
	SPATIAL MODELS
13	Object Recognition Architectures	PDF MOV
14	Object Detection	PDF MOV
15	Metric Learning	PDF MOV
16	Pixel Labeling Tasks	PDF MOV
17	Optical Flow	PDF MOV
18	Segmentation Aware Filtering	PDF MOV
	VISUALIZATION
19	Understanding ConvNets	PDF MOV
20	Texture Synthesis	PDF MOV
21	Style Transfer	PDF MOV
	SEQUENCE MODELS
22	Recurrent Neural Network (RNN)	PDF MOV
23	Long Short-Term Memory (LSTM)	PDF MOV
24	Bidirectional RNN	PDF MOV
25	Transformers	PDF MOV
26	Vision and Language	PDF MOV
27	Action Recognition	PDF MOV
	SELF-SUPERVISED LEARNING
27	Look Ma No Labels: Learning Without Labels	PDF MOV
	GEOMETRIC DEEP LEARNING
28	Graph Neural Networks	PDF MOV
	GENERATIVE MODELS
29	Generative Models Introduction	PDF MOV
30	PixelNN (PixelRNN and PixelCNN)	PDF MOV
31	Variational Autoencoder (VAE)	PDF MOV
32	Invertible Density Models - Normalizing Flows	PDF MOV
33	Generative Adversarial Network (GAN)	PDF MOV
34	Diffusion Models	PDF MOV
35	Flow Matching	PDF MOV
	ADVERSARIAL EXAMPLES
36	Adversarial Examples	PDF MOV

Useful resources.
     Terence Parr and Jeremy Howard, The Matrix Calculus You Need for Deep Learning, arXiv
     Justin Johnson, Python NumPy tutorial
     Basic Linear algebra review
     Zico Kolter, Linear algebra review and reference
     Kaare Brandt Petersen and Michael Syskind Pedersen, The Matrix Cookbook

Related courses.
     York University EECS4422/5323: Introduction to Computer Vision with Kosta Derpanis
     University of Michigan EECS 498.008/598.008: Deep Learning foir Computer Vision with Justin Johnson
     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.