Practical Deep Learning

Catalog description

This course covers the theory and technologies related to deep learning. In particular, the course focuses on the following topics: neural networks and hidden layers; issues with designing deep neural networks; convolutional neural networks (CNNs); recurrent neural networks (RNNs); generative adversarial networks (GANs); batch optimization; word embeddings; and other special topics. Graduate, professional or senior status required. Typically offered Fall Spring. Course Learning Outcomes 1. Understand basic deep learning pipeline. 2. Understand deep learning in the context of big data. 3. Understand data pre-processing techniques for deep learning. 4. Understand features and one-hot encoding. 5. Understanding simple deep neural networks. 6. Understand convolutional neural networks (CNNs). 7. Understand recurrent neural networks (RNNs). 8. Understand generative adversarial networks (GANs). 9. Understand word embeddings. 10. Understand common deep learning evaluation methods. 11. Collaborate with team members to resolve deep learning problems. 12. Conduct independent research under the instructor’s guidance. View Class Schedule