Role of Balanced Excitation and Inhibition in Modulating the Response Properties of Neural Circuit (Neocognitron)
DOI:
https://doi.org/10.26438/ijcse/v5i8.2226Keywords:
Visual Pathway, Neocognitron, Exitation and Inhibition, Artficial Neural NetworkAbstract
The visual Pathway system of our brain is very complicated to understand. The Primary visual cortex is used for the vision in our brain. These processes of vision starting from the retina to visual cortex create a long visual pathway a layer by layer approach and hierarchical connection between them. The brain consists of billions of cells for information processing known as neurons. There are two types of Neuron first is excitatory and second inhibitory .So when the information processing is is required the balance between excitation and inhibition. In this research paper we used the Neocognitron an artificial neural network for visual pathway and demonstrate using this that how role is play using the balancing of excitation and inhibition used for pattern recognition task in the various parameters. In this research paper we demonstrated that how excitation and inhibition ratio can be balanced and what happened when it become imbalanced and impact of pattern recognition and using the Neocognitron Simulator tool developed in .NET platform.
References
Fukushima K.: “Artificial vision by multi-layered neural networks: neocognitron and its advances”, Neural Networks, Vol. 37, pp 103-119 ,2013.
Fukushima K.: “Training multi-layered neural network neocognitron”, Neural Networks, Vol. 40, pp 18-3,2013.
Fukushima K.: “Interpolating vectors for robust pattern recognition”, Neural Networks, Vol. 40, Issue 8, pp 904-916,2007.
Fukushima K. and Shouno H.: “Deep convolutional network neocognitron: improved interpolating-vector”, IJCNN 2015, Killarney, Ireland,pp 1603-1610,2015.
S.U. Bohra, P.V. Ingole , "Review on Neural Network Based Approach Towards English Handwritten Alphanumeric Characters Recognition", International Journal of Computer Sciences and Engineering, Vol.1, Issue.3, pp.22-25, 2013.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
