Title :
Varied order iterative learning law for BPNN
Author :
XiaoLei Chen ; Ning Chen
Author_Institution :
Nanjing Forestry Univ., Nanjing, China
Abstract :
In this paper, we discussed respective superiority what back propagation neural network based on fractional differential and integer-order differential have, from two aspects-convergent speed and error. Then in order to get better convergent effect, the paper proposes the neural network of adaptive order. The detailed progress what is verified by MATLAB is illustrated in figures as follows.
Keywords :
backpropagation; differential equations; iterative methods; neural nets; BPNN; MATLAB; adaptive order; aspects-convergent error; aspects-convergent speed; back propagation neural network; convergent effect; fractional differential; integer-order differential; varied order iterative learning law; Adaptive systems; Biological neural networks; Convergence; Fractional calculus; Neurons; Training; Back propagation neural network; Fractional differential; Integer-order differential;
Conference_Titel :
Control and Decision Conference (CCDC), 2013 25th Chinese
Conference_Location :
Guiyang
Print_ISBN :
978-1-4673-5533-9
DOI :
10.1109/CCDC.2013.6561138
