Deep Neural Networks - 605.742

This course provides a practical introduction to the deep neural networks (DNN) with the goal to extend student’s understanding of the latest and cutting-edge technology and concepts in the deep learning (DL) field. The course starts with a brief review of and competitions in machine learning (ML) and neural networks (NN), including model evaluation techniques and feature/model engineering in Python with TensorFlow (TF) and Keras. It then defines and exemplifies the DL with convolutional neural networks (CNN), recurrent neural networks (RNN), long-short term memory (LSTM) networks with attention mechanism, generative adversarial networks (GAN) and deep reinforcement learning (DRL), transfer learning, etc.. This is a hands-on course with significant Python coding requirements and weekly ML/DL team competitions. Students will apply NN to computer vision (CV), natural language processing (NLP), and structured data tasks. Since DL is a rapidly developing field, the course will also rely on recent seminal publications.

Course Prerequisite(s)

A course in Machine Learning