How to Fail Interpretability Research

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=jXkhcoZ9W24


Duration: 44:42
1,323 views
27

Been Kim (Google Brain)
https://simons.berkeley.edu/talks/tba-90
Emerging Challenges in Deep Learning



Other Videos By Simons Institute for the Theory of Computing


2019-08-27Zero Knowledge from Multi-Party Computation
2019-08-27Succinct Arguments (Part II)
2019-08-27Succinct Arguments (Part I)
2019-08-26Probabilistically Checkable Proofs (Part II)
2019-08-26Probabilistically Checkable Proofs (Part I)
2019-08-26Interactive Proofs (Part II)
2019-08-26Interactive Proofs (Part I)
2019-08-08Designing Robust Learners
2019-08-08Better Learning from the Past: Counterfactual / Batch RL
2019-08-08Inherent Trade-offs with the Local Explanations Paradigm
2019-08-08How to Fail Interpretability Research
2019-08-07The Measure and Mismeasure of Fairness
2019-08-07Integrating Constraints into Deep Learning Architectures with Structured Layers
2019-08-07Towards Verified Deep Learning
2019-08-07Reinforcement Learning via an Optimization Lens
2019-08-06Reinforcement Learning in Recommender Systems: Some Challenges
2019-08-06Off-policy Policy Optimization
2019-08-06Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes
2019-08-06On the Hardness of Reinforcement Learning With Value-function Approximation
2019-08-06Reinforcement Learning in Feature Space: Complexity and Regret
2019-08-05Flexible Neural Networks and the Frontiers of Meta-Learning


Tags:
Emerging Challenges in Deep Learning
Been Kim
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley