Title :
Extending SpikeProp
Author :
Schrauwen, Benjamin ; Van Campenhout, Jan
Author_Institution :
Dept. of Electron. & Inf. Syst., Ghent Univ., Belgium
Abstract :
This paper introduces enhancements to the SpikeProp algorithm (S. M. Bohte, et al., 2002), an error-backpropagation learning rule suited for spiking neurons using exact spike time coding. These enhancements provide additional learning rules for the synaptic delays, time constants and for the neurons´ thresholds. This results in less constrained network topologies (the XOR problem for example needs up to 10 times less weights and learning convergence is up to two times faster).
Keywords :
backpropagation; neural nets; SpikeProp algorithm; error-backpropagation learning rule; spike time coding; spiking neurons; Biomembranes; Computer architecture; Computer networks; Convergence; Delay effects; Information systems; Network topology; Neural network hardware; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1379954
