Title :
Statistical analysis of the single-layer backpropagation algorithm. II. MSE and classification performance
Author :
Bershad, Neil J. ; Shynk, John J. ; Feintuch, Paul L.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA
fDate :
2/1/1993 12:00:00 AM
Abstract :
For pt.I see ibid., p.583-91, 1993. The analysis of pt.I is extended to the evaluation of the mean-square error and the probability of correct classification. It is shown that the mean-square error and the corresponding performance surface are such that the single-layer perceptron is prevented from correctly classifying with probability one until the weights converge at infinity
Keywords :
backpropagation; decision theory; error statistics; neural nets; nonlinear systems; parameter estimation; classification performance; decision theory; mean-square error; nonlinear system identification; performance surface; single-layer backpropagation algorithm; single-layer perceptron; statistical analysis; weight convergence; Aircraft propulsion; Backpropagation algorithms; Covariance matrix; Difference equations; Fluctuations; H infinity control; Performance evaluation; Probability; Statistical analysis; Steady-state;
Journal_Title :
Signal Processing, IEEE Transactions on
