Name
Abstract | ||
|---|---|---|
This paper presents a synaptic weight association training (SWAT) algorithm for spiking neural networks (SNNs). SWAT merges the Bienenstock-Cooper-Munro (BCM) learning rule with spike timing dependent plasticity (STDP). The STDP/BCM rule yields a unimodal weight distribution where the height of the plasticity window associated with STDP is modulated causing stability after a period of training. The SNN uses a single training neuron in the training phase where data associated with all classes is passed to this neuron. The rule then maps weights to the classifying output neurons to reflect similarities in the data across the classes. The SNN also includes both excitatory and inhibitory facilitating synapses which create a frequency routing capability allowing the information presented to the network to be routed to different hidden layer neurons. A variable neuron threshold level simulates the refractory period. SWAT is initially benchmarked against the nonlinearly separable Iris and Wisconsin Breast Cancer datasets. Results presented show that the proposed training algorithm exhibits a convergence accuracy of 95.5% and 96.2% for the Iris and Wisconsin training sets, respectively, and 95.3% and 96.7% for the testing sets, noise experiments show that SWAT has a good generalization capability. SWAT is also benchmarked using an isolated digit automatic speech recognition (ASR) system where a subset of the TI46 speech corpus is used. Results show that with SWAT as the classifier, the ASR system provides an accuracy of 98.875% for training and 95.25% for testing. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/TNN.2010.2074212 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
cancer,learning (artificial intelligence),medical computing,pattern classification,speech recognition,ASR system,BCM learning rule,Bienenstock-Cooper-Munro learning rule,SNN,STDP,SWAT,TI46 speech corpus,Wisconsin breast cancer datasets,classification problems,frequency routing capability,iris datasets,isolated digit automatic speech recognition system,spike timing dependent plasticity window,spiking neural network training algorithm,synaptic weight association training algorithm,unimodal weight distribution,variable neuron threshold level,Automatic speech recognition,Bienenstock–Cooper—Munro,dynamic synapses,spike timing dependent plasticity,spiking neural networks | Computer science,Artificial intelligence,Classifier (linguistics),Artificial neural network,Spiking neural network,Pattern recognition,Algorithm,Speech recognition,BCM theory,Learning rule,Spike-timing-dependent plasticity,Process capability index,Synaptic weight,Machine learning | Journal |
Volume | Issue | ISSN |
21 | 11 | 1045-9227 |
Citations | PageRank | References |
62 | 2.15 | 18 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| John J. Wade | 1 | 102 | 8.91 |
| McDaid, L.J. | 2 | 104 | 5.22 |
| Jose A. Santos | 3 | 204 | 12.58 |
| Heather M Sayers | 4 | 62 | 2.15 |