Modeling neural coding in the auditory midbrain with high resolution and accuracy

Abstract

Computational models of auditory processing can be valuable tools for research and technology development. Models of the cochlea are highly accurate and widely used, but models of the auditory brain lag far behind in both performance and penetration. Here, we present ICNet, a model that provides accurate simulation of neural dynamics in the inferior colliculus across a wide range of sounds, including near-perfect simulation of responses to speech. We developed ICNet using deep learning and large-scale intracranial recordings from gerbils, addressing three key modeling challenges that are common across all sensory systems: capturing the full statistical complexity of neuronal response patterns; accounting for physiological and experimental non-stationarity; and extracting features of sensory processing that are common across different brains. ICNet can be used to simulate activity from thousands of neural units or to provide a compact representation of central auditory processing through its latent dynamics, facilitating a wide range of hearing and audio applications.