Conference Paper (published)

From Fitness Landscapes to Explainable AI and Back

Details

Citation

Thomson S, Adair J, Brownlee A & van den Berg D (2023) From Fitness Landscapes to Explainable AI and Back. In: GECCO '23 Companion. Gecco '23: The Genetic and Evolutionary Computation Conference, Lisbon, 15.07.2023-19.07.2023. New York: ACM. https://doi.org/10.1145/3583133.3596395

Abstract
We consider and discuss the ways in which search landscapes might contribute to the future of explainable artificial intelligence (XAI), and vice versa. Landscapes are typically used to gain insight into algorithm search dynamics on optimisation problems; as such, it could be said that they explain algorithms and that they are a natural bridge between XAI and evolutionary computation. Despite this, there is very little existing literature which utilises landscapes for XAI, or which applies XAI techniques to landscape analysis. This position paper reviews the existing works, discusses possible future avenues, and advocates for increased research effort in this area

Keywords
Fitness Landscapes; Search Landscapes; Neural Networks; Explainable AI; XAI

StatusPublished
Publication date31/07/2023
Publication date online24/07/2023
PublisherACM
Place of publicationNew York
ISBN979-8-4007-0120-7
ConferenceGecco '23: The Genetic and Evolutionary Computation Conference
Conference locationLisbon
Dates

People (2)

Dr Jason Adair

Dr Jason Adair

Lecturer in Data Science, Computing Science

Dr Sandy Brownlee

Dr Sandy Brownlee

Senior Lecturer in Computing Science, Computing Science and Mathematics - Division