Insights, breakthroughs, and practical tips from my involvement in machine learning research.
Latest post
Foundation Models for Sequential Decision-Making
In this post, I'm hoping to give some sort of timeline of advances made in fields like reinforcement learning and robotics that I believe could be important to know about or might be important to realize AI embodied in the real world.e will start by reviewing some classical papers that combine Transformers with reinforcement learning for multi-task control. Then, we will look at some more recent advances that are used in simulated open-ended environments, and from there on we will move on to advances in control for real-world robotics with robotics foundation models.
· decision-making
Series · 9 parts
CS-330: Deep Multi-Task and Meta Learning
1 Mar 2024 – 30 Mar 2024
- 01 Deep Multi-Task and Meta Learning - Introduction
- 02 Lecture 1: Multi-Task Learning
- 03 Lecture 2: Transfer Learning and Meta-Learning
- 04 Lecture 3: Black-Box Meta-Learning & In-Context Learning
- 05 Lecture 4: Optimization-Based Meta-Learning
- 06 Lecture 5: Few-Shot Learning via Metric Learning
- 07 Lecture 6: Unsupervised Pre-Training: Contrastive Learning
- 08 Lecture 7: Unsupervised Pre-Training: Reconstruction-Based Methods
- 09 Lecture 8: Variational Inference