On December 5, 2019 there was a Mathematics in Industry Seminar
The speakers were Drs. Stephen Shauger, Sean Lynch, and Aaron Wiechmann from the Laboratory for Analytic Sciences
Abstract:
How do we know that we can trust our machine learning models? How do we detect when an adversary is exploiting our machine learning solutions? How does the explainability of machine learning models help the customers of such models versus helping the adversaries of such models? In this talk we will examine recent issues in Machine Learning Explainability and in Adversarial Machine Learning.