date | lecture | title |
2023-04-03 | Lecture 1 | Introduction |
2023-04-07 | Lecture 2 | Non-stationary linear regression |
2023-04-10 | Lecture 3 | Q-learning, a simple RL agent |
2023-04-12 | Lecture 4 | Adapting to non-stationarities |
2023-04-17 | Lecture 5 | Continual back-propagation |
2023-04-19 | Lecture 6 | Mark Ring's take on continual learning |
2023-04-24 | Lecture 7 | David Abel's take on continual learning |
2023-04-26 | Lecture 8 | Elastic weight consolidation and language models |
2023-05-01 | Lecture 9 | Continual learning: a deep learning perspective |
2023-05-03 | Lecture 10 | Bandit learning and heuristic exploration strategies |
2023-05-08 | Lecture 11 | Continual learning in the era of (very) large models |
2023-05-10 | Lecture 12 | Bandits and non-stationary bandits |
2023-05-15 | Lecture 13 | Non-Stationary bandit learning and information theory |
2023-05-17 | Lecture 14 | Information-theoretic analysis of forgetting and plasticity |
2023-05-22 | Lecture 15 | Information theory and continual learning |
2023-05-24 | Lecture 16 | An information-theoretic interpretation of CL |
2023-05-31 | Lecture 17 | Learning targets & rate-distortion theory
|