Title :
Notice of Retraction
Study on Double Weights iterative algorithm for BP neutral networks
Author_Institution :
Dept. Math. & Mech., Heilongjiang Inst. of Sci. & Technol., Harbin, China
Abstract :
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
To enhance the training speed of neural network traditional BP algorithm, takes 3 layer neural networks as an example, through the analysis and optimization for weights derives the improved BP algorithm - Double Weights iterative optimization method. By comparison of this algorithm and the traditional algorithm, the new algorithm can save training time under the premise of ensuring the accuracy, and summarized the characteristics of the algorithm.
Keywords :
backpropagation; iterative methods; neural nets; BP neural networks; backpropagation; double weights iterative algorithm; double weights iterative optimization method; BP algorithm; double weights iterative optimization method; neural network;
Conference_Titel :
Natural Computation (ICNC), 2011 Seventh International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9950-2
DOI :
10.1109/ICNC.2011.6022075
