Name
Abstract | ||
|---|---|---|
In this paper, we discuss the self-organization and formation of neural circuits based on temporal coding hypothesis. We employ an integrate-and-fire neuron model. The same spatio–temporal pattern is provided to all of the neurons in a network, and the network learns the pattern based on spike-time-dependent learning. The network should select appropriate connections in order to distributedly preserve the input pattern. Since the same input is provided to all of the neurons, competitive learning should proceed. The competitive learning is induced by background random inputs (noise). After the learning, the network works as a spatio–temporal filter for the input patterns. The effect of noise in our model is also discussed theoretically. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1016/j.neucom.2003.09.013 | Neurocomputing |
Keywords | Field | DocType |
Spike-time-dependent learning,Spiking neurons,Delay lines,Self-organization,Associative learning | Competitive learning,Biological neuron model,Computer science,Self-organization,Coding (social sciences),Artificial intelligence,Associative learning,Biological neural network,Leabra,Machine learning | Journal |
Volume | Issue | ISSN |
61 | C | 0925-2312 |
Citations | PageRank | References |
1 | 0.34 | 3 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ken-ichi Amemori | 1 | 7 | 2.90 |
| Shin Ishii | 2 | 239 | 34.39 |