论文信息 - Chaotically Oscillating Sigmoid Function in Feedforward Neural Network

Chaotically Oscillating Sigmoid Function in Feedforward Neural Network

In this study, we propose the feedfor- ward neural network with chaotically oscillating sig- moid function. By computer simulations, we confirm that the proposed neural network can find good solu- tions in early time of the back propagation learning process.

Yoshifumi Nishio | Yoko Uwate

[1] Mark E. Oxley,et al. Physiologically motivated image fusion for object detection using a pulse coupled neural network , 1999, IEEE Trans. Neural Networks.

[2] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[3] Akio Ushida,et al. Markov Chain Modeling of Intermittency Chaos and Its Application to Hopfield NN , 2004 .

[4] Willi-Hans Steeb,et al. Auditory two-tone suppression from a subcritical Hopf cochlea , 2005 .

[5] M. Kawato,et al. Hierarchical neural network model for voluntary movement with application to robotics , 1988, IEEE Control Systems Magazine.

[6] R Stoop,et al. Two-tone suppression and combination tone generation as computations performed by the Hopf cochlea. , 2004, Physical review letters.

[7] Terrence J. Sejnowski,et al. Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[8] Yoshifumi Nishio,et al. PERFORMANCE OF CHAOS AND BURST NOISES INJECTED TO THE HOPFIELD NN FOR QUADRATIC ASSIGNMENT PROBLEMS , 2004 .

[9] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .