Inhibitory normalization of error signals improves learning in neural circuits

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Eyono, Roy Henha, Levenstein, Daniel, Ghosh, Arna, Cornford, Jonathan, Richards, Blake
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915872023511040
author Eyono, Roy Henha
Levenstein, Daniel
Ghosh, Arna
Cornford, Jonathan
Richards, Blake
author_facet Eyono, Roy Henha
Levenstein, Daniel
Ghosh, Arna
Cornford, Jonathan
Richards, Blake
contents Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to changes in the distribution of their inputs. In artificial neural networks (ANNs), normalization is used to improve learning in tasks that involve complex input distributions. However, it is unclear whether inhibition-mediated normalization in biological neural circuits also improves learning. Here, we explore this possibility using ANNs with separate excitatory and inhibitory populations trained on an image recognition task with variable luminosity. We find that inhibition-mediated normalization does not improve learning if normalization is applied only during inference. However, when this normalization is extended to include back-propagated errors, performance improves significantly. These results suggest that if inhibition-mediated normalization improves learning in the brain, it additionally requires the normalization of learning signals.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17676
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Inhibitory normalization of error signals improves learning in neural circuits
Eyono, Roy Henha
Levenstein, Daniel
Ghosh, Arna
Cornford, Jonathan
Richards, Blake
Neurons and Cognition
Artificial Intelligence
Machine Learning
Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to changes in the distribution of their inputs. In artificial neural networks (ANNs), normalization is used to improve learning in tasks that involve complex input distributions. However, it is unclear whether inhibition-mediated normalization in biological neural circuits also improves learning. Here, we explore this possibility using ANNs with separate excitatory and inhibitory populations trained on an image recognition task with variable luminosity. We find that inhibition-mediated normalization does not improve learning if normalization is applied only during inference. However, when this normalization is extended to include back-propagated errors, performance improves significantly. These results suggest that if inhibition-mediated normalization improves learning in the brain, it additionally requires the normalization of learning signals.
title Inhibitory normalization of error signals improves learning in neural circuits
topic Neurons and Cognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.17676