Summary

Proceedings of the 2012 International Symposium on Nonlinear Theory and its Applications

2012

Session Number:C3L-B

Session:

Number:715

Performance of Multi-Layer Perceptron with Neurogenesis

Yuta Yokoyama,  Chihiro Ikuta,  Yoko Uwate,  Yoshifumi Nishio,  

pp.715-718

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.1.715

PDF download (1.4MB)

Neurogenesis is that new neurons are generated in the human brain. The new neurons create new network. It is known that the neurogenesis causes the improvement of memory, learning, and thinking ability by combining new neurons with biological neural network. We consider that the neurogenesis can be applied to an artificial neural network.
In this study, we propose the Multi-Layer Perceptron (MLP) with neurogenesis and apply to pattern recognition. In the MLP with neurogenesis, some neurons are generated in a hidden layer. We propose random, periodic and chaotic timing methods to introduce neurogenesis. We compare the performance of the MLP with neurogenesis with the conventional MLP.

[1] S. Becker, J. M. Wojtowicz, “A Model of Hippocampal Neurogenesis in Memory and Mood Disorders,” Cognitive Sciences, vol. 11, no. 2, pp. 70-76, 2007.

[2] R. A. Chambers, M. N. Potenza, R. E. Hoffman, W. Miranker, “Simulated Apotosis/Neurogenesis Regulates Learning and Memory Capabilities of Adaptive Neural Networks,” Neuropsychopharmacology, pp. 747-758, 2004.

[3] D.E. Rumelhart, G.E. Hinton and R.J. Williams, “Learning Representations by Back Propagation Error,” Nature, vol. 323-9, pp. 533-536, 1986.

[4] D.E. Rumelhart, J.L. McClelland, and the PDP Research Group, “Parallel distributed processing,” MIT Press, 1986.