Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence

TL;DR

This paper introduces advanced activity dependence in evolved developmental neural networks, significantly improving multitasking capabilities and environmental adaptability by regulating neural parameters like health, position, and bias.

Contribution

It extends activity dependence in developmental ANNs, demonstrating notable performance improvements in multitasking and environmental regulation.

Findings

Enhanced neural parameter control via activity dependence

Improved multitasking performance in evolved ANNs

Potential for better environmental adaptability

Abstract

Recently, Cartesian Genetic Programming has been used to evolve developmental programs to guide the formation of artificial neural networks (ANNs). This approach has demonstrated success in enabling ANNs to perform multiple tasks while avoiding catastrophic forgetting. One unique aspect of this approach is the use of separate developmental programs evolved to regulate the development of separate soma and dendrite units. An opportunity afforded by this approach is the ability to incorporate Activity Dependence (AD) into the model such that environmental feedback can help to regulate the behavior of each type of unit. Previous work has shown a limited version of AD (influencing neural bias) to provide marginal improvements over non-AD ANNs. In this work, we present promising results from new extensions to AD. Specifically, we demonstrate a more significant improvement via AD on new neural parameters including health and position, as well as a combination of all of these along with bias. We report on the implications of this work and suggest several promising directions for future work.