Homeostatic plasticity improves signal propagation in continuous-time recurrent neural networks

Continuous-time recurrent neural networks (CTRNNs) are potentially an excellent substrate for the generation of adaptive behaviour in artificial autonomous agents. However, node saturation effects in these networks can leave them insensitive to input and stop signals from propagating. Node saturation is similar to the problems of hyper-excitation and quiescence in biological nervous systems, which are thought to be avoided through the existence of homeostatic plastic mechanisms. Analogous mechanisms are implemented in CTRNNs and are shown to increase node sensitivity and improve signal propagation. These results are found in a variety of network architectures and lend support to the view that homeostatic plasticity may prevent quiescence and hyper-excitation in biological nervous systems.

• Type: Journal
• Year: 2007
• Where: BIOSYSTEMS
• Authors: Hywel T. P. Williams, Jason Noble
• Keywords: Artificial Autonomous Agents, Biological Nervous Systems, BIOSYSTEMS 2007, Node Saturation