Europhysics Letters (EPL) · 1990 · 114 citations · 7 references
Artificial IntelligenceNetwork Generalization AbilityEngineeringMachine LearningNetwork AnalysisNetwork ModelSimple Perceptron-like DevicesData ScienceData MiningPattern RecognitionSparse Neural NetworkComputational Learning TheoryMachine Learning ModelTraining ExamplesKnowledge DiscoveryComputer EngineeringComputer ScienceDeep LearningNeural Architecture SearchGeneralization AbilityNetwork ScienceHigh-dimensional NetworkBrain-like Computing
We show that the generalization ability of simple Perceptron-like devices is strongly enhanced by allowing the network itself to select the training examples. Analytic and numerical results are obtained for the Hebb and for the optimal Perceptron learning rule, respectively.
7