P. Kuhlmann et Kr. Muller, ON THE GENERALIZATION ABILITY OF DILUTED PERCEPTRONS, Journal of physics. A, mathematical and general, 27(11), 1994, pp. 3759-3774
A linearly separable Boolean function is learned by a diluted perceptr
on with optimal stability. A different level of dilution is allowed fo
r teacher and student perceptron. The learning algorithms used were th
e optimal annealed dilution and Hebbian dilution. The generalization a
bility, i.e. the probability to recognize a pattern which has not been
learned before, is calculated in replica symmetry.