PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Supervised Learning in Multilayer Spiking Neural Networks
Ioana Sporea and Andre Gruning
Neural Computation 2012.

Abstract

We introduce a supervised learning algorithm for multilayer spiking neural networks. The algorithm overcomes a limitation of existing learning algorithms: It can be applied to neurons firing multiple spikes in artificial neural networks with hidden layers. It can further in principle be used with any linearisable neuron model and allows different coding schemes of spike train patterns. The algorithm is applied successfully to classic linearly non-separable benchmarks, such as the XOR problem and the Iris data set, as well as to more complex classification and mapping problems. The algorithm has also been successfully tested in the presence of noise, requires smaller networks than reservoir computing and results in faster convergence than existing algorithms for similar tasks such as SpikeProp.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:9574
Deposited By:Andre Gruning
Deposited On:22 September 2012