Abstract | ||
---|---|---|
In this paper, a physiological fuzzy neural network is proposed, which shows more improved learning time and convergence property than that of the conventional fuzzy neural network. First, we investigate the structure of physiological neurons of the nervous system and propose new neuron structure based on fuzzy logic. And by using the proposed fuzzy neuron structures, the model and learning algorithm of physiological fuzzy neural network are proposed. We applied the proposed algorithm to 3-bit parity problem. The experiment results showed that the proposed algorithm reduces the possibility of local minima more than the conventional single layer perceptron does, and improves the time and convergence for learning. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11539902_149 | ICNC (3) |
Keywords | Field | DocType |
convergence property,fuzzy logic,physiological fuzzy neural network,proposed fuzzy neuron structure,conventional fuzzy neural network,new neuron structure,conventional single layer perceptron,proposed algorithm,3-bit parity problem,physiological neuron,local minima,nervous system,fuzzy neural network | Convergence (routing),Neuro-fuzzy,Computer science,Fuzzy logic,Maxima and minima,Time delay neural network,Artificial intelligence,Adaptive neuro fuzzy inference system,Artificial neural network,Perceptron,Machine learning | Conference |
Volume | ISSN | ISBN |
3612 | 0302-9743 | 3-540-28320-X |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
kwangbaek kim | 1 | 110 | 43.94 |
Hae-Ryong Bea | 2 | 0 | 0.34 |
Chang-Suk Kim | 3 | 4 | 2.49 |