Inferring the basis of binaural detection with a modified autoencoder

Smith, Samuel; Sollini, Joseph; Akeroyd, Michael A.

doi:10.3389/fnins.2023.1000079

Authors

SAMUEL SMITH Samuel.Smith4@nottingham.ac.uk
Assistant Professor

JOSEPH SOLLINI JOSEPH.SOLLINI@NOTTINGHAM.AC.UK
Nottingham Research Fellow

Professor MICHAEL AKEROYD MICHAEL.AKEROYD@NOTTINGHAM.AC.UK
Professor of Hearing Sciences

Abstract

The binaural system utilizes interaural timing cues to improve the detection of auditory signals presented in noise. In humans, the binaural mechanisms underlying this phenomenon cannot be directly measured and hence remain contentious. As an alternative, we trained modified autoencoder networks to mimic human-like behavior in a binaural detection task. The autoencoder architecture emphasizes interpretability and, hence, we “opened it up” to see if it could infer latent mechanisms underlying binaural detection. We found that the optimal networks automatically developed artificial neurons with sensitivity to timing cues and with dynamics consistent with a cross-correlation mechanism. These computations were similar to neural dynamics reported in animal models. That these computations emerged to account for human hearing attests to their generality as a solution for binaural signal detection. This study examines the utility of explanatory-driven neural network models and how they may be used to infer mechanisms of audition.

Citation

Smith, S., Sollini, J., & Akeroyd, M. A. (2023). Inferring the basis of binaural detection with a modified autoencoder. Frontiers in Neuroscience, 17, Article 1000079. https://doi.org/10.3389/fnins.2023.1000079

Journal Article Type	Article
Acceptance Date	Jan 2, 2023
Online Publication Date	Jan 26, 2023
Publication Date	Jan 26, 2023
Deposit Date	Jan 4, 2023
Publicly Available Date	Jan 26, 2023
Journal	Frontiers in Neuroscience
Print ISSN	1662-4548
Electronic ISSN	1662-453X
Publisher	Frontiers Media
Peer Reviewed	Peer Reviewed
Volume	17
Article Number	1000079
DOI	https://doi.org/10.3389/fnins.2023.1000079
Keywords	General Neuroscience
Public URL	https://nottingham-repository.worktribe.com/output/15712787
Publisher URL	https://www.frontiersin.org/articles/10.3389/fnins.2023.1000079/full