Title | ||
---|---|---|
Varying scales wavelet neural network based on entropy function and its application in channel equalization |
Abstract | ||
---|---|---|
This paper proposes a new kind of neural network named varying scales wavelet neural network to reduce wavelet-neuron number and simplify network structure. In order to avoid the local minima, entropy function is used as penalty function. The new network is applied to channel equalization, simulation results demonstrate that this network has less wavelet-neurons and recursive steps and can converge to the global minimum. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11427469_52 | ISNN (3) |
Keywords | Field | DocType |
new kind,network structure,entropy function,new network,neural network,recursive step,simulation result,channel equalization,local minimum,varying scale,global minimum,penalty function,local minima | Equalization (audio),Computer science,Stochastic neural network,Maxima and minima,Binary entropy function,Probabilistic neural network,Artificial intelligence,Artificial neural network,Recursion,Machine learning,Penalty method | Conference |
Volume | ISSN | ISBN |
3498 | 0302-9743 | 3-540-25914-7 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingyan Jiang | 1 | 67 | 11.96 |
Dongfeng Yuan | 2 | 86 | 8.55 |
Shouliang Sun | 3 | 0 | 0.34 |