Skip to content

Schedule (Spring 2023)


  • Introduction to CSC 561
  • Introduction to Neural Networks, Perceptron, MLPs
  • Width vs Depth in MLPs
  • Empirical Risk Minimization, Learning
  • Gradient Descent
  • Backpropagation: Forward, Backward, Vectorization
  • Computational Graphs, Autograd, Pytorch
  • Optimization: Hessian methods, Momentum, Nesterov
  • Optimization: SGD and Mini-Batch Gradient Descent
  • Optimization: Adagrad, RMSProp, Adam
  • Batch Normalization, L1/L2 Regularization, Dropout, Data Augmentation
  • Activation Functions, Weight Initialization
  • Model Selection
  • Convolutions and Correlation Filters (1d, 2d)
  • Convolutional Neural Networks (CNNs)
  • CNN Architectures
  • Visualization of CNN Filters and Activations
  • Word2Vec, n-Gram and Neural Language Models, RNNs, LSTMs
  • Neural Machine Translation, Attention
  • Self-Attention, Transformers
  • Generative Models, Autoencoders, VAEs, GANs
  • Graph Neural Networks

ML Tools -- Workshop Series

Placeholder Placeholder

This GitHub repository contains all materials covered during URI's Spring 2023 Machine Learning Workshop Series. We are excited to make the most of this opportunity to expose the community to some introductory Machine Learning tools and techniques, and hope to successfully foster an interest of these topics in all of you.

Assignments / Exams

  • Assignment 1 (Mar 6)
  • Assignment 2 (Mar 24)
  • Midterm Exam (Apr 4)
  • Technical Paper Presentation (TBD)
  • Project Proposal (Apr 12)
  • Project Final Report (May 10)
  • Project Presentation (May 10)