Neuromodulated Learning in Deep Neural Networks

TL;DR

This paper introduces a biologically inspired neuromodulation approach to deep neural network training, dynamically adjusting learning parameters during training to improve adaptability and performance.

Contribution

It presents a novel method of deep artificial neuromodulation that applies evolved, dynamic, location-specific learning strategies to neural networks, unlike static hyper-parameters.

Findings

Neuromodulation improves learning adaptability.

Evolved dynamics generalize across models and problems.

Location-specific strategies emerge from evolution.

Abstract

In the brain, learning signals change over time and synaptic location, and are applied based on the learning history at the synapse, in the complex process of neuromodulation. Learning in artificial neural networks, on the other hand, is shaped by hyper-parameters set before learning starts, which remain static throughout learning, and which are uniform for the entire network. In this work, we propose a method of deep artificial neuromodulation which applies the concepts of biological neuromodulation to stochastic gradient descent. Evolved neuromodulatory dynamics modify learning parameters at each layer in a deep neural network over the course of the network's training. We show that the same neuromodulatory dynamics can be applied to different models and can scale to new problems not encountered during evolution. Finally, we examine the evolved neuromodulation, showing that evolution found dynamic, location-specific learning strategies.