Information based explanation methods for deep learning agents—with applications on large open-source chess models

With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: the question of how to explain the domain knowledge internalised by such models, and the problem that such models are not made open...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 14; no. 1; pp. 20174 - 10
Main Authors: Hammersborg, Patrik, Strümke, Inga
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 30.08.2024
Nature Publishing Group
Nature Portfolio
Subjects:
639/705/117
639/705/258
Deep learning
Humanities and Social Sciences
Initiatives
Methods
multidisciplinary
Neural networks
Science
Science (multidisciplinary)
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: the question of how to explain the domain knowledge internalised by such models, and the problem that such models are not made openly available. This work presents the re-implementation of the concept detection methodology applied to AlphaZero, by using large, open-source chess models with comparable performance. We obtain results similar to those achieved when applying this methodology to AlphaZero, while relying solely on open-source resources. We also present a novel explainable AI (XAI) method, which is guaranteed to highlight exhaustively and exclusively the information used by the explained model. This method generates visual explanations tailored to domains characterised by discrete input spaces, as is the case for chess. Our presented method has the desirable property of controlling the information flow between any input vector and the given model, which in turn provides strict guarantees regarding what information is used by the trained model during inference. We demonstrate the viability of our method by applying it to standard 8 × 8 chess, using large open-source chess models.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-70701-2