Implementing Fuzzy Reasoning on a Spiking Neural Network

Authors:
Cornelius Glackin;Liam Mcdaid;Liam Maguire;Heather Sayers
Affiliations:
Faculty of Engineering, School of Computing & Intelligent Systems, University of Ulster, Londonderry, Northern Ireland BT48 7JL;Faculty of Engineering, School of Computing & Intelligent Systems, University of Ulster, Londonderry, Northern Ireland BT48 7JL;Faculty of Engineering, School of Computing & Intelligent Systems, University of Ulster, Londonderry, Northern Ireland BT48 7JL;Faculty of Engineering, School of Computing & Intelligent Systems, University of Ulster, Londonderry, Northern Ireland BT48 7JL
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 3
Cited 2

Neural networks with dynamic synapses

Neural Computation
Learning Temporally Encoded Patterns in Networks of SpikingNeurons

Neural Processing Letters
Receptive field optimization for ensemble encoding

Neural Computing and Applications

Receptive field optimisation and supervision of a fuzzy spiking neural network

Neural Networks
A new learning algorithm for adaptive spiking neural networks

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train frequencies. The receptive fields behave in a similar manner as fuzzy membership functions. The network is supervised but learning only occurs locally as in the biological case. The connectivity of the hidden and output layers is representative of a fuzzy rule base. The advantages and disadvantages of the network topology for the IRIS classification task are demonstrated and directions of current and future work are discussed.