Open Access Open Access  Restricted Access Subscription or Fee Access

Simple Single Neural Net in Pattern Classification Hebbian and Perceptron Rule - A Review

Dr. P. Radha, T. Shanthi

Abstract


This review paper introduces the basic concepts of pattern recognition, the underlying system architecture and provides the understanding of various research models and related algorithms for pattern classification. In this paper, we discuss three methods of training a simple, single layer neural network for pattern classification: the hebb rule, the perceptron rule. We conclude the paper with comparison of the two nets .The process of recognizing patterns and classifying data accordingly has been gaining interest from a long time and human beings have developed highly sophisticated skills for sensing from their environment and take actions according to what they observe.


Keywords


Feature Extraction, Face Recognition, Error Back Propagation, Gradient Descent Rule, Neural Network.

Full Text:

PDF

References


“Fundamentals of neural networks” arctectures, algorithm and application by Laurence Fauselt.

“Viewpoint invariant face recognition usingin dependent component analysis and attractor networks” Marian Stewart Bartlett Terrence J. Sejnowski.

“Access control by face recognition using neural networks” dmitry bryliuk and valery starovoitov .

This project was supported by Lawrence Livermore National Laboratory ISCR Agreement B291528, and by the McDonnell-Pew Center for Cognitive Neuroscience at San Diego. References

Bartlett, M. Stewart, & Sejnowski, T. , 1996. Unsupervised learning of invariant representations of faces throu h temporal association. Computational Neuroscience: Int. Rev. Neurobio. Suppl. 1 J Bower, Ed., Academic Prcss, San Diego, CA: 317-322.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.