|
|||||
|
|
| Distributed Parameter Neural Networks via Adaptive Wavelet | |
| 引用本文： | Shi Zhuoer,Jiao Licheng and Bao ZhengNational Radar Signal Processing Lab. and Center for Neural Networks,Xidian University,Xi''''an 710071P.R.China. Distributed Parameter Neural Networks via Adaptive Wavelet[J]. 系统工程与电子技术(英文版), 1993, 0(2) |
| 作者姓名： | Shi Zhuoer Jiao Licheng and Bao ZhengNational Radar Signal Processing Lab. and Center for Neural Networks Xidian University Xi''''an 710071P.R.China |
| 作者单位： | Shi Zhuoer，Jiao Licheng and Bao ZhengNational Radar Signal Processing Lab. and Center for Neural Networks，Xidian University，Xi'an 710071P.R.China |
| 基金项目： | The project is supported by the NSFC |
| 摘 要： | The paper outlines a new neural net (DPNN) for describing brain's action based on one-dimensional cable theory. While the traditional neural network system only finding its character involving time changing (as HNN, BP etc.), the model-DPNNs (distributed parameter neural networks) are not only the transmitted neurons of time variation, but also the functions of positions by the voltage u(x. I). With the neuroscientific relevance, some bionural features like intermittent conduction and dendritic spike are fixed well by DPNNs which considered as complicated and adaptive devices contract to the functional elementary units. To find the semi-analytical representation of DPNNs, adaptive wavelets are utilized as new microlocalization tools. While maintaining all advantages of wavelet function, the adaptive wavelet offers a viable alternative learning procedure to the orthogonal least squares method (OLS), Adaptive wavelet method develops a fairly general, low-cost multiscale method for neural net optimization. |
Distributed Parameter Neural Networks via Adaptive Wavelet |
|
| Shi Zhuoer,Jiao Licheng and Bao ZhengNational Radar Signal Processing Lab. and Center for Neural Networks,Xidian University,Xi'an P.R.China. Distributed Parameter Neural Networks via Adaptive Wavelet[J]. Journal of Systems Engineering and Electronics, 1993, 0(2) | |
| Authors: | Shi Zhuoer Jiao Licheng Bao ZhengNational Radar Signal Processing Lab. Center for Neural Networks Xidian University Xi'an P.R.China |
| Affiliation: | Shi Zhuoer,Jiao Licheng and Bao ZhengNational Radar Signal Processing Lab. and Center for Neural Networks,Xidian University,Xi'an 710071P.R.China |
| Abstract: | The paper outlines a new neural net (DPNN) for describing brain's action based on one-dimensional cable theory. While the traditional neural network system only finding its character involving time changing (as HNN, BP etc.), the model-DPNNs (distributed parameter neural networks) are not only the transmitted neurons of time variation, but also the functions of positions by the voltage u(x. I). With the neuroscientific relevance, some bionural features like intermittent conduction and dendritic spike are fixed well by DPNNs which considered as complicated and adaptive devices contract to the functional elementary units. To find the semi-analytical representation of DPNNs, adaptive wavelets are utilized as new microlocalization tools. While maintaining all advantages of wavelet function, the adaptive wavelet offers a viable alternative learning procedure to the orthogonal least squares method (OLS), Adaptive wavelet method develops a fairly general, low-cost multiscale method for neural net optimization. In addition, a Lyapunov function method is also used to study the uniform asymptotic stability of DPNNs to support the new theory. |
| Keywords: | Distributed parameter neural networks Adaptive wavelet Neural net optimization Lyapunov function method. |
| 本文献已被 CNKI 等数据库收录！ | |