Neuromodulated Learning in Deep Neural Networks
This work addresses the limitation of fixed hyperparameters in deep learning, offering a novel approach inspired by neuroscience, though it appears incremental as it builds on existing gradient descent methods.
The authors tackled the problem of static, uniform learning parameters in deep neural networks by proposing deep artificial neuromodulation, which applies biological neuromodulation concepts to stochastic gradient descent, resulting in evolved dynamic and location-specific learning strategies that can scale to new problems.
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.