Fast sigmoidal networks via spiking neurons
Neural Computation
The handbook of brain theory and neural networks
Lower bounds for the computational power of networks of spiking neurons
Neural Computation
Stochastic training of a biologically plausible spino-neuromuscular system model
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Implementing Fuzzy Reasoning on a Spiking Neural Network
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Building a bridge between spiking and artificial neural networks
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
SWAT: a spiking neural network training algorithm for classification problems
IEEE Transactions on Neural Networks
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Supervised learning in multilayer spiking neural networks
Neural Computation
A new supervised learning algorithm for spiking neurons
Neural Computation
| Hi-index | 0.00 |
Networks of spiking neurons are very powerful and versatile models forbiological and artificial information processing systems. Especially formodelling pattern analysis tasks in a biologically plausible way thatrequire short response times with high precision they seem to be moreappropriate than networks of threshold gates or models that encode analogvalues in average firing rates. We investigate the question how neurons canlearn on the basis of time differences between firing times. In particular,we provide learning rules of the Hebbian type in terms of single spikingevents of the pre- and postsynaptic neuron and show that the weightsapproach some value given by the difference between pre- and postsynapticfiring times with arbitrary high precision.