Deep Learning Theory and Applications

Catalog description

This course takes a principled and hands-on approach to deep learning with neural networks, covering machine learning basics, backpropagation, stochastic gradient descent, regularization, and universality. Topics include CNNs, GANs, RNNs, GCNs, autoencoders, transformers, and other modern architectures and training techniques. Additional coursework is required for those enrolled in the graduate-level course.