Neural Computation
November 1995, Vol. 7, No. 6, Pages 1206-1224
(doi: 10.1162/neco.1995.7.6.1206)
Learning and Generalization with Minimerror, A Temperature-Dependent Learning Algorithm
Article PDF (811.31 KB)
Abstract
We study the numerical performances of Minimerror, a recently introduced learning algorithm for the perceptron that has analytically been shown to be optimal both on learning linearly and nonlinearly separable functions. We present its implementation on learning linearly separable boolean functions. Numerical results are in excellent agreement with the theoretical predictions.