Tutorial: Safe and Reliable Machine Learning

TL;DR

This tutorial provides an overview of methods and best practices for ensuring safety and reliability in machine learning systems, emphasizing fairness, accountability, and transparency considerations.

Contribution

It offers a comprehensive summary of current techniques and challenges in developing safe and reliable machine learning models, aimed at practitioners and researchers.

Findings

Highlights key safety and reliability techniques

Discusses challenges in deploying trustworthy ML systems

Provides resources and references for further learning

Abstract

This document serves as a brief overview of the "Safe and Reliable Machine Learning" tutorial given at the 2019 ACM Conference on Fairness, Accountability, and Transparency (FAT* 2019). The talk slides can be found here: https://bit.ly/2Gfsukp, while a video of the talk is available here: https://youtu.be/FGLOCkC4KmE, and a complete list of references for the tutorial here: https://bit.ly/2GdLPme.