Call for Paper - July 2019 Edition
IJCA solicits original research papers for the July 2019 Edition. Last date of manuscript submission is June 20, 2019. Read More

Study of Evolutionary Connectionism from the perspective of Fuzzy Neural Network and Neuro-Fuzzy Inference model

Print
PDF
2nd National Conference on Information and Communication Technology
© 2011 by IJCA Journal
Number 1 - Article 3
Year of Publication: 2011
Authors:
Rajesh S. Prasad

Rajesh S Prasad. Article: Study of Evolutionary Connectionism from the perspective of Fuzzy Neural Network and Neuro-Fuzzy Inference model. IJCA Proceedings on 2nd National Conference on Information and Communication Technology NCICT(8):19-23, November 2011. Full text available. BibTeX

@article{key:article,
	author = {Rajesh S. Prasad},
	title = {Article: Study of Evolutionary Connectionism from the perspective of Fuzzy Neural Network and Neuro-Fuzzy Inference model},
	journal = {IJCA Proceedings on 2nd National Conference on Information and Communication Technology},
	year = {2011},
	volume = {NCICT},
	number = {8},
	pages = {19-23},
	month = {November},
	note = {Full text available}
}

Abstract

Connectionism is a movement in cognitive science which hopes to explain human intellectual abilities using neural networks (also known as ‘neural nets’). Evolutionary Connectionist System is an adaptive, incremental learning and knowledge representation system that evolves its structure and functionality, where in the core of the system is a connectionist architecture that consists of neurons (information processing units) and connections between them. Neural networks are simplified models of the brain composed of large numbers of units (the analogs of neurons) together with weights that measure the strength of connections between the units. These weights model the effects of the synapses that link one neuron to another. Experiments on models of this kind have demonstrated an ability to understand information, adapt knowledge and evolve intelligence.

Fuzzy neural networks are connectionist architectures that are trained as neural networks, but their structure can be interpreted as a et of fuzzy rules. In contrast to them, neuro-fuzzy inference systems consist of a set of rules and an inference method that are embodied or combined with a connectionist structure for a better adaption.

This paper aims to explore the fuzzy neural approach and neurofuzzy inference system to amalgamate evolutionary connectionism and constitutes a challenge to classicism which has been a matter of hot debate in recent years.

Reference

  • Amari, S. and Kasabov, N., “Brain-like Computing and Intelligent Information System, Springer Verlag, Singapore.
  • Arbib M, “The Handbook of Brain Theory and Neural Networks”, MIT Press, Cambridge, MA, (1995, 2002).
  • Nikola Kasabov, “Evolving Connectionist Systems”, Springer, Second Edition, 978-1-84628-345-1.
  • Elman, Jeffrey L., “Distributed representations, Simple recurrent networks, and grammatical Structure”, Machine Learning, 7, pp. 195-225.
  • Kasabov N. AND Kozma R., “ Neuro-Fuzzy Techniques for Intelligent Information System”, Physical Verlag (Springer Verlag), Heidelberg, 1999.
  • Rajesh Prasad, U.V. Kulkarni, “A Novel Evolutionary Connectionist Text Summarizer”, International Conference on Anticounterfeiting, Security and Identification, ASID 2009, HongKong, by IEEE HongKong section.
  • J. L. Elman, “Distributed representations, simple recurrent networks, and grammatical structure,” Machine Learning, vol. 7, pp. 195–225, 1991.
  • Rajesh Prasad, U.V. Kulkarni, “Connectionist Approach to Generic Text Summarization”, WASET, International Conference on Neural Networks, Oslo, Norway, July 2008.