Unsupervised and Reinforcement Learning
| Course Code | COMP-257 |
|---|---|
| Lecture hours per week | 2 |
| Lab hours per week | 2 |
| Course Availability | Open |
| Description | In the first half of this course, students will be introduced to unsupervised learning (dimensionality reduction, k-means clustering, hierarchical clustering, Gaussian mixtures, autoencoders, and Kohonen Self-Organizing Maps (SOM)). In the second half of the course, students will be introduced to reinforcement learning (policy gradient, Markov decision processes, Q-learning, and the TF-Agents library). Students will gain hands-on experience by applying unsupervised learning and reinforcement learning techniques. |