Quick Overview: In the first segment of the workshop, Professor Hima Lakkaraju motivates the need for interpretable Professor Hima Lakkaraju presents some of the latest advancements in post hoc explanations for black-box Professor Hima Lakkaraju describes how explanation methods can be compared and evaluated. Interpretability evaluation ...
Stanford Seminar Ml Explainability Part - Detailed Overview & Context
In the first segment of the workshop, Professor Hima Lakkaraju motivates the need for interpretable Professor Hima Lakkaraju presents some of the latest advancements in post hoc explanations for black-box Professor Hima Lakkaraju describes how explanation methods can be compared and evaluated. Interpretability evaluation ... Professor Hima Lakkaraju presents some of the latest advancements in Professor Hima Lakkaraju discusses the many future research directions for building February 17, 2023 Q. Vera Liao of Microsoft Research Artificial Intelligence technologies are increasingly used to aid human ...
Dr. Matthew Gombolay, Assistant Professor of Interactive Computing at the Georgia Institute of Technology November 18, 2022 ... May 17, 2024 Aaron Shaw, Northwestern University Increasingly, Large Language Models (LLMs) are used to simulate human ... October 20, 2023 Leo Zhicheng Liu of University of Maryland A tight coupling of humans and machines is often required to ... October 7, 2022 Dakuo Wang of MIT-IBM Watson AI Lab Human-Centered AI (HCAI) refers to the research effort that aims to ... Avanti Shrikumar's talk on "Interpretable deep learning methods for regulatory genomics" including DeepLIFT and TF-MoDISco. "Deep Learning For Dummies" - Carey Nachenberg of Symantec and UCLA CS
