Context-modulation of hippocampal dynamics and deep convolutional networks

TL;DR

This paper explores how biological circuit complexity influences neural computation and demonstrates that incorporating context-sensitive biases in deep networks significantly enhances performance on image classification tasks.

Contribution

It introduces a biologically inspired mechanism for context-modulation in neural networks, improving performance without increasing network size.

Findings

Context-sensitive biases improve classification accuracy.

Biological circuit principles can enhance artificial neural network performance.

Performance gains achieved without increasing network complexity.

Abstract

Complex architectures of biological neural circuits, such as parallel processing pathways, has been behaviorally implicated in many cognitive studies. However, the theoretical consequences of circuit complexity on neural computation have only been explored in limited cases. Here, we introduce a mechanism by which direct and indirect pathways from cortex to the CA3 region of the hippocampus can balance both contextual gating of memory formation and driving network activity. We implement this concept in a deep artificial neural network by enabling a context-sensitive bias. The motivation for this is to improve performance of a size-constrained network. Using direct knowledge of the superclass information in the CIFAR-100 and Fashion-MNIST datasets, we show a dramatic increase in performance without an increase in network size.