Title | ||
---|---|---|
An individual adaptive gain parameter backpropagation algorithm for complex-valued neural networks |
Abstract | ||
---|---|---|
The complex-valued backpropagation algorithm has been widely used. However, the local minima problem usually occurs in the process of learning. We proposed an individual adaptive gain parameter backpropagation algorithm for complex-valued neural network to solve this problem. We specified the gain parameter of the sigmoid function in the hidden layer for each learning pattern. The proposed algorithm is tested by benchmark problem. The simulation results show that it is capable of preventing the complex-valued network learning from sticking into the local minima. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11759966_82 | ISNN (1) |
Keywords | Field | DocType |
complex-valued network,gain parameter,local minima problem,complex-valued backpropagation algorithm,individual adaptive gain parameter,backpropagation algorithm,benchmark problem,complex-valued neural network,proposed algorithm,local minimum,local minima,neural network | Gain parameter,Computer science,Maxima and minima,Artificial intelligence,Adaptive algorithm,Backpropagation,Artificial neural network,Machine learning,Sigmoid function | Conference |
Volume | ISSN | ISBN |
3971 | 0302-9743 | 3-540-34439-X |
Citations | PageRank | References |
2 | 0.35 | 5 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Li Songsong | 1 | 24 | 3.76 |
Toshimi Okada | 2 | 10 | 1.73 |
Xiaoming Chen | 3 | 6 | 1.83 |
Zheng Tang | 4 | 183 | 24.78 |