Inhibitory normalization of error signals improves learning in neural circuits
This addresses the problem of understanding biological learning mechanisms for researchers in computational neuroscience, but it is incremental as it builds on existing normalization methods.
The study investigated whether inhibitory normalization in neural circuits improves learning by testing ANNs with excitatory and inhibitory populations on an image recognition task with variable luminosity, finding that performance significantly improved only when normalization was applied to back-propagated errors, not just during inference.
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.