Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016) — mentioned by blueblob

Mon, 05 Jun 2017 16:54:25 GMT

This is an area that fades in and out of focus with such venues as the Workshop on Human Interpretability in Machine Learning (WHI) [1]. It's becoming increasingly important when it comes to auditability and understanding of what is actually learned by algorithm. Avoiding classifiers from learning to discriminate based on age, race, etc [2] or in domains where it's important to know what the algorithm is doing such as medicine. Work in understanding DL is not really interpretable in any domain, typically they train another (simpler, less accurate) model and use that to explain what the model…

Paper and discussion history. A mention is not an endorsement.

Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016) · HackerPapers discussions

Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016) — mentioned by blueblob