Curriculum
  /  
Descriptions
MLDS 490-24: Advanced Algorithms for Machine Learning


VIEW ALL COURSE TIMES AND SESSIONS

Description

This course covers three major algorithmic topics in machine learning. Half of the course is devoted to reinforcement learning with the focus on the policy gradient and deep Q-network algorithms. The remaining material covers algorithms for federated learning including differential privacy concepts, and autoML algorithms based on Bayesian optimization, genetic programming, and hyperband. Development in python and tensorflow is required.

The main objectives are:

  1. Given a business problem identify if reinforcement learning is needed to solve it or a different technique. Recognize states, the role of an agent, its actions, and environment for a given reinforcement learning problem.
  2. Select the most appropriate reinforcement learning algorithm for a problem at hand.
  3. Given distributed data, identify the type of the federated learning setting and apply the most appropriate family of algorithms.
  4. Understand autoML parameters and algorithmic choices.