Neuronal Synchrony in Complex-Valued Deep Networks

TL;DR

This paper introduces complex-valued neural units incorporating phase information to model neuronal synchrony, enhancing the biological plausibility and functional versatility of deep networks.

Contribution

It presents a novel complex-valued neural network formulation that captures spike timing and synchrony, bridging biological mechanisms with deep learning models.

Findings

Captures aspects of neuronal synchrony such as gating and dynamic binding

Demonstrates potential in simple experiments for representing distributed objects

Suggests synchrony as a flexible mechanism for multiple functions in deep networks

Abstract

Deep learning has recently led to great successes in tasks such as image recognition (e.g Krizhevsky et al., 2012). However, deep networks are still outmatched by the power and versatility of the brain, perhaps in part due to the richer neuronal computations available to cortical circuits. The challenge is to identify which neuronal mechanisms are relevant, and to find suitable abstractions to model them. Here, we show how aspects of spike timing, long hypothesized to play a crucial role in cortical information processing, could be incorporated into deep networks to build richer, versatile representations. We introduce a neural network formulation based on complex-valued neuronal units that is not only biologically meaningful but also amenable to a variety of deep learning frameworks. Here, units are attributed both a firing rate and a phase, the latter indicating properties of spike timing. We show how this formulation qualitatively captures several aspects thought to be related to neuronal synchrony, including gating of information processing and dynamic binding of distributed object representations. Focusing on the latter, we demonstrate the potential of the approach in several simple experiments. Thus, neuronal synchrony could be a flexible mechanism that fulfills multiple functional roles in deep networks.