February 12, 2021

A project-based graduate course aimed to provide practical and fundamental skills to perform research with deep-learning in engineering and physical sciences.

The course will be an adaptation of the course that was taught in Sp19: https://canvas.uw.edu/courses/1272847

In a nutshell, we will introduce current topics and methods in deep learning and Artificial Neural Networks (ANNs) and describe the underlying principles of making neural networks generic computing frameworks. We will then build computational skills for training neural networks, understanding and working with algorithms related to different architectures of ANNs:

1) Convolutional Neural Network Models (CNNs)
2) Sequence Neural Network Models (RNNs)
3) Generative Variational and Adversarial Neural Network Models (VAE/GANs)

4) Deep Reinforcement Learning

Machine Learning knowledge is recommended (but not required).
Due to expected interest, the course might get overbooked. If that happens, please contact instructor Eli Shlizerman shlizee@uw.edu