Abstract | ||
---|---|---|
In this paper we propose SPAN, a LIF spiking neuron that is capable of learning input-output spike pattern association using a novel learning algorithm. The main idea of SPAN is transforming the spike trains into analog signals where computing the error can be done easily. As demonstrated in an experimental analysis, the proposed method is both simple and efficient achieving reliable training results even in the context of noise. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-24958-7_83 | ICONIP |
Keywords | Field | DocType |
main idea,reliable training result,spike train,precise-time spike pattern association,experimental analysis,lif spiking neuron,input-output spike pattern association,supervised learning,spiking neural networks | Pattern recognition,Computer science,Supervised learning,Artificial intelligence,Analog signal,Spiking neural network,Neuron,Machine learning | Conference |
Volume | ISSN | Citations |
7063 | 0302-9743 | 3 |
PageRank | References | Authors |
0.49 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ammar Mohemmed | 1 | 140 | 6.71 |
Stefan Schliebs | 2 | 380 | 18.56 |
Nikola K Kasabov | 3 | 3645 | 290.73 |