Short Description

An introduction to optimization for machine learning. Computation of derivatives. Deep learning.

Learning Outcomes

By the end of the course, students are expected to be able to:

  1. Formulate various machine learning problems as optimization problems.
  2. Implement gradient descent and compare/contrast with stochastic gradient descent.
  3. Avoid common numerical errors due to rounding error.
  4. Compare/contrast different ways of computing derivatives (symbolic/automatic/numerical differentiation).
  5. Train neural networks for performing regression and classification tasks with deep learning.
  6. Deploy neural networks on a GPU.

Reference Material

Instructor (2016-2017)

Note: information on this page is preliminary and subject to change.