STAT-4744: Deep Learning

Description: Introduction to deep learning, including algorithms, theoretical motivations, and implementation in practice. Basic neural network architectures and optimizations. Multilayer perceptrons, backpropagation, automatic differentiation, and stochastic gradient descent. Convolutional neural networks, recurrent neural networks and the attention mechanism. Generative models, variational autoencoders, and generative adversarial networks. Reinforcement learning, Q learning and design of simple AI systems. Python programming language. Emphasis on efficient implementation, optimization, and scalability. Creation of deep learning models in the context of different types of real applications such as image classification and language processing.

Pathways: N/A

Course Hours: 3 credits

Corequisites: N/A

Crosslist: N/A

Repeatability: N/A