Abstract
| Language | English |
|---|---|
| Pages | 247-256 |
| Journal | Neural Networks |
| Volume | 24 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - Apr 2011 |
Fingerprint
Cite this
}
Receptive Field Optimisation and Supervision of a Fuzzy Spiking Neural Network. / Glackin, Neil; Maguire, LP; McDaid, Liam; Sayers, Heather.
In: Neural Networks, Vol. 24, No. 3, 04.2011, p. 247-256.Research output: Contribution to journal › Article
TY - JOUR
T1 - Receptive Field Optimisation and Supervision of a Fuzzy Spiking Neural Network
AU - Glackin, Neil
AU - Maguire, LP
AU - McDaid, Liam
AU - Sayers, Heather
PY - 2011/4
Y1 - 2011/4
N2 - 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 firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.
AB - 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 firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.
U2 - 10.1016/j.neunet.2010.11.008
DO - 10.1016/j.neunet.2010.11.008
M3 - Article
VL - 24
SP - 247
EP - 256
JO - Neural Networks
T2 - Neural Networks
JF - Neural Networks
SN - 0893-6080
IS - 3
ER -