Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)

TL;DR

This document compiles the proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning, featuring invited talks and discussions on making machine learning models more understandable to humans.

Contribution

It provides a collection of recent research, insights, and expert perspectives on interpretability in machine learning from the 2017 workshop.

Findings

Highlights key challenges in interpretability

Showcases new methods for explainability

Summarizes expert opinions and future directions

Abstract

This is the Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), which was held in Sydney, Australia, August 10, 2017. Invited speakers were Tony Jebara, Pang Wei Koh, and David Sontag.