MSA 8600 - Deep learning analytics

1.5 Hours
This is an introductory and review course on historical development of neural networks and state-of-the-art approaches to deep learning. Students will learn the various deep learning methods and will also learn how to design neural network architectures and training procedures through hands-on assignments. The course covers a variety of topics including neutral network basics, deep learning strategies such as GPU training and regulation, convolutional networks, recurrent neutral networks, the long short-term memory and other gated RNNs and unsupervised deep learning. Applications of using deep learning into natural language processing and image recognition will be discussed throughout the course. May be repeated but only if content varies.

Prerequisite(s): None.
Corequisite(s): None.
Pre/Corequisite(s): None.
Requirements: None.