BMI 539A Deep Learning I

Credits: 3
Deep neural networks (DNNs) have recently demonstrated superiority to other machine learning techniques in a variety of tasks ranging from speech recognition and natural language processing to computer vision. This course covers a number of topics in machine learning with a specific focus on deep neural networks (DNNs) including model capacity, regularization, overview of optimization techniques, perceptron algorithm and multi-layer perceptron, feed-forward neural networks, convolutional networks, and sequence-to-sequence models. The topics are purposely chosen to cover all the background material that students need to effectively train DNNs through supervised techniques in their research problems. The course will also draw from applications in speech and language processing. Recommended background of this course includes programming proficiency in Python or Matlab, enough knowledge of calculus, linear algebra and probability theory. The course will be a combination of Introductory lectures and a few toy examples in Python. The course also requires a final project of interest to students chosen in consultation with the instructor. The project requires a written report and a final presentation.

Graded: A-F
May be taken only once for credit
Also offered as: BMI 639A