Predictive Coding Light+: learning to predict visual sequences with spike timing-dependent plasticity and synaptic delays

TL;DR

Predictive Coding Light+ (PCL+) is a spiking neural network model that learns to predict visual sequences by maintaining recent past information through recurrent connections with delays.

Contribution

The paper introduces PCL+, a novel spiking neural network architecture that learns recurrent excitatory connections with delays for sequence prediction.

Findings

PCL+ reproduces classic sequence learning in visual cortex.

PCL+ successfully fills in missing input in gesture recognition.

PCL+ demonstrates how spiking networks can predict future sensory input.

Abstract

The ability to predict the future is of great value for biological and artificial cognitive systems alike. However, successfully predicting the future typically requires maintaining a memory of the recent past. It is currently unclear how biological or artificial spiking neural networks can learn to maintain past sensory information to help predict the future. Here we propose Predictive Coding Light+ (PCL+), a spiking neural network architecture for unsupervised sequence processing that learns recurrent excitatory connections with delays to enable short-term retention of information. We show that the PCL+ network reproduces classic findings on sequence learning in visual cortex. Furthermore, it learns to ``fill in'' missing input in a challenging gesture recognition task. Overall, our work shows how spiking neural networks can learn recurrent excitatory connections with delays to maintain a record of the recent past and successfully predict the future.