Heterogeneous Neural Networks for Adaptive Behavior in Dynamic Environments

Research in artificial neural networks has genera1ly emphasized homogeneous architectures. This heterogeneity is crucial to the flexible generation of behavior which is essential for survival in a complex, dynamic environment. It may also provide powerful insights into the design of artificial neural networks. In this paper, we describe a heterogeneous neural network for controlling the wa1king of a simulated insect. This controller is inspired by the neuroethological It exhibits a and neurobiological literature on insect locomotion.