Abstract | ||
---|---|---|
We propose a novel supervised learning rule allowing the training of a precise input-output behavior to a spiking neuron. A single neuron can be trained to associate (map) different output spike trains to different multiple input spike trains. Spike trains are transformed into continuous functions through appropriate kernels and then Delta rule is applied. The main advantage of the method is its algorithmic simplicity promoting its straightforward application to building spiking neural networks (SNN) for engineering problems. We experimentally demonstrate on a synthetic benchmark problem the suitability of the method for spatio-temporal classification. The obtained results show promising efficiency and precision of the proposed method. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-23957-1_25 | IFIP Advances in Information and Communication Technology |
Keywords | Field | DocType |
Spiking Neural Networks,Supervised Learning,Spatio-temporal patterns | Continuous function,Delta rule,Computer science,Supervised learning,Input/output,Artificial intelligence,Spiking neural network,Train | Conference |
Volume | ISSN | Citations |
363 | 1868-4238 | 6 |
PageRank | References | Authors |
0.56 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ammar Mohemmed | 1 | 140 | 6.71 |
Stefan Schliebs | 2 | 380 | 18.56 |
Satoshi Matsuda | 3 | 135 | 8.40 |
Nikola K Kasabov | 4 | 3645 | 290.73 |