Tools and Practices for Responsible AI Engineering

01/14/2022
by   Ryan Soklaski, et al.
0

Responsible Artificial Intelligence (AI) - the practice of developing, evaluating, and maintaining accurate AI systems that also exhibit essential properties such as robustness and explainability - represents a multifaceted challenge that often stretches standard machine learning tooling, frameworks, and testing methods beyond their limits. In this paper, we present two new software libraries - hydra-zen and the rAI-toolbox - that address critical needs for responsible AI engineering. hydra-zen dramatically simplifies the process of making complex AI applications configurable, and their behaviors reproducible. The rAI-toolbox is designed to enable methods for evaluating and enhancing the robustness of AI-models in a way that is scalable and that composes naturally with other popular ML frameworks. We describe the design principles and methodologies that make these tools effective, including the use of property-based testing to bolster the reliability of the tools themselves. Finally, we demonstrate the composability and flexibility of the tools by showing how various use cases from adversarial robustness and explainable AI can be concisely implemented with familiar APIs.

READ FULL TEXT

page 1

page 5

research
03/09/2022

Towards a Roadmap on Software Engineering for Responsible AI

Although AI is transforming the world, there are serious concerns about ...
research
09/07/2023

Beyond XAI:Obstacles Towards Responsible AI

The rapidly advancing domain of Explainable Artificial Intelligence (XAI...
research
02/08/2021

Multisource AI Scorecard Table for System Evaluation

The paper describes a Multisource AI Scorecard Table (MAST) that provide...
research
10/21/2018

Challenge AI Mind: A Crowd System for Proactive AI Testing

Artificial Intelligence (AI) has burrowed into our lives in various aspe...
research
12/30/2022

ComplAI: Theory of A Unified Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models

The advances in Artificial Intelligence are creating new opportunities t...
research
10/27/2020

A Fast, Scalable, Universal Approach For Distributed Data Aggregations

In the current era of Big Data, data engineering has transformed into an...
research
10/07/2021

Automated Testing of AI Models

The last decade has seen tremendous progress in AI technology and applic...

Please sign up or login with your details

Forgot password? Click here to reset