Skip to content

Schedule (Spring 2022)

Lectures

  • Introduction to CSC 561
  • Introduction to Neural Networks, Perceptron, MLPs
  • Neural Network Representation, Width x Depth
  • Learning, Empirical Risk Minimization
  • Gradient Descent
  • Backpropagation, Vector Formulation
  • Optimization
  • Normalization, Regularization
  • Convolutional Neural Networks
  • CNN Architectures
  • Training (activation, initialization, hyperparameters, transfer learning, data augmentation)
  • Recurrent Neural Networks, LSTMs
  • Language Models, Sequence to Sequence, Attention
  • Transformers
  • Generative Models, Autoencoders, Variational Autoencoders, GANs
  • Graph Neural Networks

Assignments

  • Assignment 1 (due Feb 28)
  • Assignment 2 (due Mar 21)
  • Assignment 3 (due Apr 4)
  • Assignment 4 (due Apr 18)
  • Paper Presentations/Videos (due Apr 24)
  • Project Abstract (due Apr 12)
  • Project Poster (due May 5)
  • Project Report (due May 9)