Proceedings Article10.1109/ICICIC.2007.202
BP Neural Network Structure Optimization Algorithm Based on Polynomial Regression
Rao Hong,Fu Ming-fu,Chen Lian +2 more
- 05 Sep 2007
- pp 562-562
1
TL;DR: A self-configuring algorithm based on polynomial regression is presented, and simulations of the modified algorithm in MATLAB indicate that an improved BP network is achieved, with the optimum number of neurons of the hidden layers.
read more
Abstract: To design a streamlined network structure is a commonly used method for BP neural network to guarantee the neural network's generalization. Self- configuration algorithm deletes the redundant nodes of the hidden layer to achieve the optimized structure. But it isn't effective in solving the non-linear problem due to the linear regression theory basis. Thus, a self-configuring algorithm based on polynomial regression is presented. The simulations of the modified algorithm in MATLAB indicate that an improved BP network is achieved, with the optimum number of neurons of the hidden layers.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Learning Algorithm for Feedforward Neural Networks Based on Fuzzy Controller
Chen Yan,Liang Yan,Zhai Jun,Zhou Zhou +3 more
- 17 Oct 2008
TL;DR: This paper proposes a continuous learning algorithm for feedforward neural networks, an improvement of traditional BP algorithm based on fuzzy controller, and applies it to lateral prediction for reservoir parameters, which make good performance in error control and convergence.
References
•Book
Neural network design
Martin T. Hagan,Howard B. Demuth,Mark Beale +2 more
- 29 Dec 1995
TL;DR: This book, by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules, as well as methods for training them and their applications to practical problems.
6.8K
A neural network methodology for process fault diagnosis
TL;DR: A neural-network-based methodology for providing a potential solution to the preceding problems in the area of process fault diagnosis is proposed and compared with the knowledge-based approach.
424
Generalization theory and generalization methods for neural networks
Wei Hai
- 01 Jan 2001
TL;DR: This survey reviewed the main results on generalization research, and tried to point out the relationship between generalization theory and corresponding generalization methods.
21
SuperSAB: fast adaptive back propagation with good scaling properties
TL;DR: It is shown that SuperSAB may converge orders of magnitude faster than the original back propagation algorithm, and is only slightly instable, while the algorithm is very insensitive to the choice of parameter values, and has excellent scaling properties.
Related Papers (5)
M.-S. Chen,Michael T. Manry +1 more
- 08 Jul 1991
Zhigang Zhou,Lihong Chen,Li Wan +2 more
- 06 Jun 2009