Abstract | ||
---|---|---|
In this paper, a method of improving the learning time and convergence rate isproposed to exploit theadvantages of artificial neural networks and fuzzy theory to neuron structure. This method is applied to the XOR problem, n bit parity problem, whichis used as the benchmark in neural network structure, and recognition of digit image in the vehicle plate image for practical image recognition. As a result of experiments, it does not always guarantee the convergence. However, the network was improved the learning time and has the high convergence rate. The proposed network can be extended to an arbitrary layer. Though a single layer structure is considered, the proposed method has a capability of high speedduring the learning process and rapid processing on huge patterns. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11427391_96 | ISNN (1) |
Keywords | Field | DocType |
neural network,convergence rate,digital image,image recognition,artificial neural network | Convergence (routing),Parity bit,Computer science,Artificial intelligence,Rate of convergence,Artificial neural network,Pattern recognition,Fuzzy logic,Algorithm,Neuron structure,Exploit,Perceptron,Machine learning | Conference |
Volume | ISSN | ISBN |
3496 | 0302-9743 | 3-540-25912-0 |
Citations | PageRank | References |
1 | 0.43 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
kwangbaek kim | 1 | 110 | 43.94 |
Sungshin Kim | 2 | 210 | 64.17 |
Young Hoon Joo | 3 | 738 | 76.87 |
Am-Sok Oh | 4 | 2 | 0.80 |