Steadystate Analysis of a Single-Layer Perceptron Based on a System Identification Model with Bias Terms

IEEE Transactions on Circuits and Systems

Volumn 38, Issue 9, 1991, Pages 1030-1042

  Shynk, John J ^a   Bershad, Neil J ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING SYSTEMS; MATHEMATICAL TECHNIQUES - CONVERGENCE OF NUMERICAL METHODS; PROBABILITY - RANDOM PROCESSES; SIGNAL FILTERING AND PREDICTION; SIGNAL PROCESSING;

GAUSSIAN INPUT SIGNALS; PERCEPTRON CONVERGENCE PROPERTIES; SINGLE-LAYER PERCEPTRON; SYSTEM IDENTIFICATION MODEL;

NEURAL NETWORKS;

EID: 0026220795     PISSN: 00984094     EISSN: None     Source Type: Journal    
DOI: 10.1109/31.83874     Document Type: Article

References (17)

1. R.P. Lippmann, “An introduction to computing with neural nets,” IEEE ASSP Mag., vol. 4, pp. 4–22, Apr. 1987.
2. B. Widrow, R.G. Winter, and R.A. Baxter, “Layered neural nets for pattern recognition,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 36, pp. 1109–1118, July 1988.
3. B. Widrow and S.D. Stearns, Adaptive Signal Processing. Englewood Cliffs, NJ: prentice-Hall, 1985.
4. F. Rosenblatt, Principles of Neurodynamics. New York: Spartan, 1962.
5. J.J. Shynk and S. Roy, “Convergence properties and stationary points of a perceptron learning algorithm,” Proc. IEEE, vol. 78, pp. 1599–1604, Oct. 1990.
6. J.J. Shynk, “A perceptron convergence model for Gaussian input signals,” in Proc. European Signal Processing Conf., pp. 1619–1622, Sept. 1990.
7. J.J. Shynk and N.J. Bershad, “Convergence analysis of a single-layer perceptron based on a system identification model,” in Proc. 24th Asilomar Conf. Signals, Systems, Computers, pp. 1003–1008, Nov. 1990.
8. N.J. Bershad, “On error saturation nonlinearities in LMS adaptation,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-36, pp. 440–452, Apr. 1988.
9. D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D.E. Rumelhart and J.L. McClelland, Eds. Cambridge, MA: MIT Press, 1986, pp. 318–362.
10. R. Price, “A useful theorem for nonlinear devices having Gaussian inputs,” IRE Trans. Inform. Theory, vol. IT-4, pp. 69–72, June 1958.
11. E.L. McMahon, “An extension of Price's theorem,” IEEE Trans. Inform. Theory, vol. IT-10, p. 168, Apr. 1964.
12. R.F. Pawula, “A modified version of Price's theorem,” IEEE Trans. Inform. Theory, vol. IT-13, pp. 285–288, Apr. 1967.
13. N.J. Bershad, “Nonlinear quantization effects in the LMS and block LMS adaptive algorithms-A comparison,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-37, pp. 1504–1512, Oct. 1989.
14. N.J. Bershad, “On weight update saturation nonlinearities in LMS adaptation,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-38, pp. 623–630, Apr. 1990.
15. J.J. Shynk, “Performance surfaces of a single-layer perceptron,” IEEE Trans. Neural Networks, vol. 1, pp. 268–274, Sept. 1990.
16. J.J. Bussgang, “Cross-correlation functions of amplitude-distorted Gaussian signals,” Tech. Rep. 216, Research Laboratory of Electronics, MIT, Cambridge, MA, Mar. 1952.
17. H.B. Dwight, Tables of Integrals and Other Mathematical Data. New York: Macmillan, 1960.