DeepAI AI Chat
Log In Sign Up

AI Explainability 360: Impact and Design

by   Vijay Arya, et al.

As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, have different explanation needs. To address these needs, in 2019, we created AI Explainability 360 (Arya et al. 2020), an open source software toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. This paper examines the impact of the toolkit with several case studies, statistics, and community feedback. The different ways in which users have experienced AI Explainability 360 have resulted in multiple types of impact and improvements in multiple metrics, highlighted by the adoption of the toolkit by the independent LF AI Data Foundation. The paper also describes the flexible design of the toolkit, examples of its use, and the significant educational material and documentation available to its users.


One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

As artificial intelligence and machine learning algorithms make further ...

OpenGridGym: An Open-Source AI-Friendly Toolkit for Distribution Market Simulation

This paper presents OpenGridGym, an open-source Python-based package tha...

Xplique: A Deep Learning Explainability Toolbox

Today's most advanced machine-learning models are hardly scrutable. The ...

Explainability Case Studies

Explainability is one of the key ethical concepts in the design of AI sy...

CLAIMED, a visual and scalable component library for Trusted AI

Deep Learning models are getting more and more popular but constraints o...

On Explainability in AI-Solutions: A Cross-Domain Survey

Artificial Intelligence (AI) increasingly shows its potential to outperf...

HistoCartography: A Toolkit for Graph Analytics in Digital Pathology

Advances in entity-graph based analysis of histopathology images have br...