Instructive artificial intelligence (AI) for human training, assistance, and explainability

Nicholas Kantack; Nina Cohen; Nathan Bos; Corey Lowman; James Everett; Timothy Endres

doi:10.1117/12.2618616

6 June 2022 Instructive artificial intelligence (AI) for human training, assistance, and explainability

Nicholas Kantack, Nina Cohen, Nathan Bos, Corey Lowman, James Everett, Timothy Endres

Proceedings Volume 12113, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV; 1211308 (2022) https://doi.org/10.1117/12.2618616
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

We propose a novel approach to explainable AI (XAI) based on the concept of "instruction" from neural networks. In this case study, we demonstrate in a human subject experiment how a superhuman neural network might instruct human trainees as an alternative to traditional approaches to XAI. Specifically, an AI examines human actions and calculates variations on the human strategy that lead to better performance. Experiments with a JHU/APL-developed AI player for the cooperative card game Hanabi suggest this technique makes unique contributions to explainability while improving human performance. One area of focus for Instructive AI is in the significant discrepancies that can arise between a human's actual strategy and the strategy they profess to use. This inaccurate self-assessment presents a barrier for XAI, since explanations of an AI's strategy may not be properly understood or implemented by human recipients. As an alternative, we propose a method of translating insights from an AI into corrections on human decision making. With neural networks, this allows a direct calculation of the changes in network weights needed to improve the human strategy to better emulate an AI that outperforms humans on certain metrics. Subjected to constraints (e.g. sparsity) these weight changes can be interpreted as recommended changes to human strategy (e.g. "value A more, and value B less"). Instruction from AI such as these functions both to help humans perform better at tasks, but also to better understand, anticipate, and correct the actions of an AI.

Conference Presentation

Citation Download Citation

Nicholas Kantack, Nina Cohen, Nathan Bos, Corey Lowman, James Everett, and Timothy Endres "Instructive artificial intelligence (AI) for human training, assistance, and explainability", Proc. SPIE 12113, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV, 1211308 (6 June 2022); https://doi.org/10.1117/12.2618616

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available