![]() |
This course will provide an elementary hands-on introduction to neural networks and deep learning. Topics covered will include: linear classifiers; multi-layer neural networks; back-propagation and stochastic gradient descent; convolutional neural networks and their applications to computer vision tasks like object detection and dense image labeling; recurrent neural networks and state-of-the-art sequence models like transformers; generative models (generative adversarial networks and variational autoencoders); and deep reinforcement learning. Coursework will consist of programming assignments in Python (primarily PyTorch). Those registered for 4 credit hours will have to complete a project.
Instructor: Svetlana Lazebnik (slazebni -at- illinois.edu)
Lectures: Mondays and Wednesdays, 11:00AM-12:15PM
TAs:
TBA
|
Prerequisites: Multi-variable calculus, linear algebra, data structures (CS 225 or equivalent), CS 361 or STAT 400. No previous exposure to machine learning is required.
Grading scheme:
Date | Topic | Assignments |
January 25 | Introduction | Self-study: Python/numpy tutorial |
January 27 | Intro to learning and classifiers | |
February 1 | Linear classifiers | |
February 3 | Linear classifiers cont. | |
February 8 | Multi-class classification | Assignment 1 out |
February 10 | Nonlinear classifiers, bias-variance tradeoff | |
February 15 | Backpropagation | |
February 22 | Convolutional networks | Assignment 1 due |
February 24 | Convolutional networks cont. | Assignment 2 out |
March 1 | Advanced training | |
March 3 | PyTorch tutorial | |
March 8 | Object detection | Assignment 2 due |
March 10 | Object detection cont. | Assignment 3 out |
March 15 | Dense prediction | |
March 17 | Dense prediction cont. | Project proposals due (for 4 credits) |
March 22 | Self-supervised learning | |
March 29 | Visualization | |
March 31 | Adversarial examples | |
April 5 | Generative adversarial networks | |
April 7 | Conditional GANs | |
April 12 | Variational autoencoders | Assignment 4 out Assignment 3 due |
April 14 | Recurrent networks | Project progress reports due |
April 19 | Sequence-to-sequence models with attention | |
April 21 | Transformers | |
April 26 | Deep Q-learning | Assignment 4 due |
April 28 | Policy gradient methods | Assignment 5 out |
May 3 | Deep RL applications and challenges | |
May 5 | Societal impacts and ethics | Assignment 5 due Final project reports due |