IJSER Home >> Journal >> IJSER
International Journal of Scientific and Engineering Research
ISSN Online 2229-5518
ISSN Print: 2229-5518 6    
Website: http://www.ijser.org
scirp IJSER >> Volume 3,Issue 6,June 2012
A Neuroplasticity (Brain Plasticity) Approach to Use in Artificial Neural Network[
Full Text(PDF, )  PP.817-825  
Yusuf Perwej , Firoj Parwej
Learning, Neuroplasticity, Multilayer Perceptron (MLP), Artificial Neural Network (ANN), Neuron, Brain, Synaptic
You may have heard that the Brain is plastic. As you know the brain is not made of plastic, Brain Plasticity also called Neuroplasticity. Brain plasticity is a physical process. Gray matter can actually shrink or thicken neural connections can be forged and refined or weakened and severed. Brain Plasticity refers to the brain's ability to change throughout life. The brain has the amazing ability to reor-ganize itself by forming new connections among brain cells (neurons). For a long time, it was believed that as we aged, the connec-tions in the brain became fixed. Research has shown that in fact the brain never stops changing through learning. Plasticity is the capacity of the brain to change with learning. Changes associated with learning occur mostly at the level of the connections among neurons. New connections can form and the internal structure of the existing synapses can change but also partially its internal topology, according to either the received external stimuli and the pre existent connection. We have found this idea can be applied also to the simple Artificial Neural Network. In this paper we have proposed a new method is presented to adapt dynamically the topology of an Artificial Neural Network using only the information on learning set. And also in this paper we have proposed algorithm has been tested on result relative to the Multilayer Perceptron (MLP) problem
[1] McCullock, W.W, Pitts, W. ,―A Logical Calculus of the Ideas Imminent in Nervous Activity‖ , Bulletin of Mathematical Biophysics, vol 5 , pp 115-133, 1943.

[2] M . Smith, ―Neural Network for Statistical Modelling‖ , Boston International Thomson Computer Press , ISBN 1-850-32842-0, 1996.

[3] E.B. Baum , and D. Haussler , ― What size net gives valid generalization‖ , Neural computation , no. 1 , pp 151-160, 1989.

[4] Pelvig, D P, Pakkenberg, H Stark, AK ,Pakkenberg B., ―Neocortical glial cell numbers in human brains‖. Neurobiology of Aging 29, vol (11), pp 1754 – 176 2, April 2007. PMID 17544173, doi:10.1016/j.neurobiolaging.2007.04.013.

[5] B. Draganski , C. Gaser , V. Busch ,G. Schuierer , U. Bogdahn , ―Neuroplasticity: changes in grey matter induced by training‖ , Nature. 427 , pp 311-312, May 2004.

[6] W. Freeman , and C. Skarda , ―Spatial EEG patterns, non-linear dynamics and perception‖ The neo-Sherringtonian vew, Brain Research Reviews 10 , pp 147-175, 1985.

[7] E. Rolls , and A. Treves , ―Neural Network in the brain involved in memory and recall‖ , In Proceedings of Internatonal Joint Conference on Neural Network, Nagoya, Japan, IEEE, pp 9-14, October 1993.

[8] W. Freeman ,― Simulation of chaotic EEG patterns with a dynamic model of the olfactory system‖ Biological Cybernetics 56 , pp 139-150, 1987.

[9] Shaw, Christopher, McEachern, Jill, eds, ―Toward a theory of neuroplasticity ‖, London, England , Psychology Press. ISBN 9781841690216., 2001.

[10] P. Rakic , ―Neurogenesis in adult primate neocortex: an evaluation of the evidence‖, Nature Reviews Neuroscience 3 (1), pp 65–71 , January 2002. doi:10.1038/nrn700, PMID 11823806.

[11] W. Eberhard, and M. J. ,‖Developmental Plasticit and Evolution ―, Oxford University Press, USA, 2003.

[12] T. Ash ,― Dynamic node creation in backpropagation network‖ , ICS Report 8901, UCSD, 1989.

[13] G. Roth , and U. Dicke ,―Evolution of the brain and Intelligence‖,Trends in Cognitive Sciences 9 (5), pp 250–257, 2005. doi:10.1016/j.tics.2005.03.005, PMID 15866152

[14] Abitz, Damgaard et al , ―Excess of neurons in the human newborn mediodorsal thalamus compared with that of the adult‖ , Oxford, Oxford Journals Cerebral Cortex Advance Access Cerebral Cortex, 11 January 2007. doi:10.1093/cercor/bhl163

[15] F. J. Pineda, ―Recurrent backpropagation and the dynamical approach to adaptive neural computations‖, Neural Computations, no 1, pp 161-172, 1989.

[16] L. Yuille , and D. Geiger , ―The Handbook of Brain Theory and Neural Networks‖ , edited by Arbib M. A. , MIT Press, Cambridge, pp 1056–1060, 1995.

Untitled Page