Tutorial: Safe and Reliable Machine 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.

Overview of the "Safe and Reliable Machine Learning" tutorial given at the 2019 ACM Conference on Fairness, Accountability, and Transparency (FAT* 2019)

References in corpus (3)

• Confounding variables can degrade generalization performance of radiological deep learning models
• A Dual Approach to Scalable Verification of Deep Networks
• Reliable Decision Support using Counterfactual Models

Cited by in corpus (8)

• Can You Trust This Prediction? Auditing Pointwise Reliability After Learning
• "The Human Body is a Black Box": Supporting Clinical Decision-Making with Deep Learning
• Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport
• Adversarial Examples for Electrocardiograms
• Know Your Model (KYM): Increasing Trust in AI and Machine Learning
• Chameleon: A Semi-AutoML framework targeting quick and scalable development and deployment of production-ready ML systems for SMEs
• Conformance Constraint Discovery: Measuring Trust in Data-Driven Systems
• Automated Dependence Plots