Deep Learning.

Catalog description

Students examine the architectures, platforms, tools, trends, and research directions of deep learning. Topics may include the relevant algorithms, techniques, and methodologies of convolutional neural networks, recurrent neural networks, auto-encoders, generative adversarial networks, gated recurrent units, long short-term memory networks, deep reinforcement learning, and recent new deep learning architectures. Students get hands-on practices for analyzing real-world large data with deep learning open-sourced frameworks and software tools. Prerequisite: Graduate Standing.