Title :
Supervised synaptic weight adaptation for a spiking neuron
Author :
Davis, Bryan A. ; Erdogmus, Deniz ; Rao, Yadunandana N. ; Principe, Jose C.
Author_Institution :
Computational NeuroEngineering Lab., Florida Univ., Gainesville, FL, USA
Abstract :
A novel algorithm named Spike-LMS is described that adapts the synaptic weights of an artificial spiking neuron to produce a desired response. The derivation of Spike-LMS follows from the derivation of the least-mean squares (LMS) algorithm used in adaptive filter theory. Spike-LMS works directly in the domain of spike trains, and therefore makes no assumptions about any particular neural encoding method. This algorithm is able to identify the synaptic weights of a spiking neuron given the pre-synaptic and post-synaptic spike trains.
Keywords :
adaptive systems; learning (artificial intelligence); least mean squares methods; neural nets; Spike-LMS; adaptive filter theory; artificial spiking neuron; least-mean squares algorithm; neural encoding method; post-synaptic spike trains; pre-synaptic spike trains; supervised synaptic weight adaptation; Adaptive filters; Cost function; Encoding; Laboratories; Least squares approximation; Neural engineering; Neural networks; Neurons; Supervised learning; System identification;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223968
