English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With large chess-playing neural network models like AlphaZero contesting thestate of the art within the world of computerised chess, two challenges presentthemselves: The question of how to explain the domain knowledge internalised bysuch models, and the problem that such models are not made openly available.This work presents the re-implementation of the concept detection methodologyapplied to AlphaZero in McGrath et al. (2022), by using large, open-sourcechess models with comparable performance. We obtain results similar to thoseachieved on AlphaZero, while relying solely on open-source resources. We alsopresent a novel explainable AI (XAI) method, which is guaranteed to highlightexhaustively and exclusively the information used by the explained model. Thismethod generates visual explanations tailored to domains characterised bydiscrete input spaces, as is the case for chess. Our presented method has thedesirable property of controlling the information flow between any input vectorand the given model, which in turn provides strict guarantees regarding whatinformation is used by the trained model during inference. We demonstrate theviability of our method by applying it to standard 8x8 chess, using largeopen-source chess models.

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