Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지

A Biological Fuzzy Multilayer Perceptron Algorithm

  • Published : 2003.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

A biologically inspired fuzzy multilayer perceptron is proposed in this paper. The proposed algorithm is established under consideration of biological neuronal structure as well as fuzzy logic operation. We applied this suggested learning algorithm to benchmark problem in neural network such as exclusive OR and 3-bit parity, and to digit image recognition problems. For the comparison between the existing and proposed neural networks, the convergence speed is measured. The result of our simulation indicates that the convergence speed of the proposed learning algorithm is much faster than that of conventional backpropagation algorithm. Furthermore, in the image recognition task, the recognition rate of our learning algorithm is higher than of conventional backpropagation algorithm.

Keywords

References

  1. Tarun Khanna, Foundation of Neural Networks, Addison Wesley, Reading, MA, 1990
  2. M. M. Gupta and J. Qi, 'On Fuzzy Neuron Models', Proc. of UCNN, Vol. 2, pp. 431-435, 1991
  3. F. Rosenblatt, Principles of Neurodynamics, Percetrons, and the Theory of Brain Mechanisms, Spartan, Washington, 1961
  4. D. E. Rummelhart, J. L. McClelland, and the PDP Research Group, Parallel Distributed Processing, Vols. 1 and 2, MIT press, Cambridge, 1986
  5. T. Yamakawa and S.Tomoda, 'A Fuzzy Neuron and its Application to pattern recognition', Proc. of the IFSA Congress, Seattle, Washington, pp.30-38, Aug. 6-11, 1989
  6. Kwang Baek Kim, Jung Pil Shin, Eui Young Cha, 'The Neuron Structure by Fuzzy Logic', Proc. of the Second Korea JCEANF'92, pp.379-387, Oct. 1992
  7. C. M. Butter, Neuropsychology: The Study of Brain and Behavior, Brooks/Cole, Belmont, CA 1968
  8. Kuffer S.W., Nicholls T.G., an Martin A.R., Form Neuron to Brain : A Cell Approch to the Function of Nervous System, 2nd ed. Sunderland, Mass. : sinauer, 1984
  9. E.R Kandel, J.H Schwartz, and T.M Jessell, 'Essentials of Neural Science and Behavior', Printice Hall, Englewood, 1995
  10. Kwang Baek Kim, Myung Kang, Eui Young Cha, 'A Fuzzy Competitive Backpropagation using Nervous System', Proc. of the World Congress on System Simulation, pp.188-1992, 1997
  11. I. Hayashi, H. Nomura and N. Wakami, 'Artifical Neural Network Driven Fuzzy Control and its Application to the Learning of Inverted Pendulum System', Proc. of the IFSA, Seattle, Washington, pp. 610-613, Aug. 6-11, 1989