
Chelsea Finn
Assistant Professor of Computer Science and Electrical Engineering · Computer Science and Electrical Engineering · Stanford University
At Prof Rod’s reading desk
Questions to explore
- What does it mean to learn a model that can adapt to a new task?
- How should adaptation be evaluated when tasks share training structure?
Research interests
Chelsea Finn studies robot learning, meta-learning and learning through interaction.
- Robot learning
- Meta-learning
- Learning through interaction
Explore the work
Prof Rod’s reading notes
Start with a paper
ICML · 2017
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Prof Rod’s reading note: Distinguish training across tasks from adapting on a new task. Check how few-shot results depend on the task split.
Bring a question of your own
Turn reading into research
Draw the training and adaptation data split for a two-task experiment. Describe one way information could leak across that boundary.
Prof Rod’s evaluation lesson helps you ask what was sampled and what a comparison supports. This is our suggested preparation, not the researcher’s admission requirement.
Learn to compare model resultsKeep exploring
More at Stanford University
Explore the universityImprove this page
Suggest a correction, share a paper to start with, or point readers to a group page or opening.