Rule Based Experiment on Exponential Integrate and Fire Neuron Model
Vishnu Kumar1, Ajeet Kumar Verma2, Rajesh Dwivedi3, Ebenezer Jangam4
1Vishnu Kumar, Department of Computer Science and Engineering, Vignan Foundation For Science Technology and Research, Guntur (Andhra Pradesh), India.
2Ajeet Kumar Verma, National Institute of Technology, (Goa), India.
3Rajesh Dwivedi, Department of Computer Science and Engineering, Vignan Foundation For Science Technology and Research, Guntur (Andhra Pradesh), India.
4Ebenezer Jangam, Department of Computer Science and Engineering, Vignan Foundation For Science Technology and Research, Guntur (Andhra Pradesh), India.
Manuscript received on 12 February 2019 | Revised Manuscript received on 02 March 2019 | Manuscript Published on 08 June 2019 | PP: 30-34 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E10060275S419/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Classification is a technique to deal with supervised learning of Artificial Neural Networks. In recent years, many methods are developed for classification. Conventional neurons are less efficient in classification accuracy. Spiking neuron is third generation neuron. Spiking neuron models are generating highly computationally accurate firing patterns of spikes. These spikes are using to process the information in human brain. So a novel learning rule is proposed for an Exponential Integrate and Fire Neuron Model. This model is used for Malaria disease prediction. We have collected dataset for malaria from govt. ID hospital, Goa. By using proposed classifier, we have obtained increased accuracy in classification of the data. Our classification results are better when compared with legacy model and Biological Neuron Model.
Keywords: IFN, MLP, EIFN, FFNN, H-H, QIFN, Learning Rule LEIFN.
Scope of the Article: Nanometer-Scale Integrated Circuits