Summary

Proceedings of the 2013 International Symposium on Nonlinear Theory and its Applications

2013

Session Number:C1L-D

Session:

Number:390

Multi-Layer Perceptron with Local Glia Connection

Chihiro Ikuta,  Yoko Uwate,  Yoshifumi Nishio,  

pp.390-393

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.2.390

PDF download (412.6KB)

In a biological system, a glia and a neuron are correlated each other. These cells closely relate and compose a higher brain function. In this study, we propose a Multi-Layer Perceptron (MLP) with local glia connection. We connect the glia to the neurons in two hidden-layer. The glias receive the outputs of the connecting neurons and the glias sum the neuron outputs. When the summed value is over the excitation threshold of the glia, the glia generates a pulse. After that, the pulse is input to the neuron threshold. Moreover, the excitation of the glia decreases the excitation threshold of neighboring glias. Thus, the neighboring glias are excited at a similar timing. We consider that the position relationship between the glia and the neuron is important to the MLP performance. By simulations, we confirm the influence of the glia for the MLP performance.

[1] P.G. Haydon, “Glia: Listening and Talking to the Synapse,” Nature Reviews Neuroscience, vol. 2, pp. 844-847, 2001.

[2] S. Koizumi, M. Tsuda, Y. Shigemoto-Nogami and K. Inoue, “Dynamic Inhibition of Excitatory Synaptic Transmission by Astrocyte-Derived ATP in Hippocampal Cultures,” Proc. National Academy of Science of U.S.A, vol. 100, pp. 11023-11028, Mar. 2003.

[3] S. Ozawa, “Role of Glutamate Transporters in Excitatory Synapses in Cerebellar Purkinje Cells,” Brain and Nerve, vol. 59, pp. 669-676, 2007.

[4] S. Kriegler and S.Y. Chiu, “Calcium Signaling of Glial Cells along Mammalian Axons,” The Journal of Neuroscience, vol. 13, pp. 4229-4245, 1993.

[5] M.P. Mattoson and S.L. Chan, “Neuronal and Glial Calcium Signaling in Alzheimer's Disease,” Cell Calcium, vol. 34, pp. 385-397, 2003.

[6] G. Perea and A. Araque, “Glial Calcium Signaling and Neuro-Glia Communication,” Cell Calcium, vol. 38, pp. 375-382, 2005.

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

[8] J.R. Alvarez-Sanchez, “Injecting knowledge into the Solution of the Two-Spiral Problem,” Neural Computing & Applications, vol. 8, pp. 265-272, 1999.

[9] H. Sasaki, T. Shiraishi and S. Morishita, “High precision learning for neural networks by dynamic modification of their network structure,” Dynamics & Design Conference, pp. 411-1-411-6, 2004.