Answers are grounded in this paper and cite their sources.
We study the equilibrium properties of the real weights linear perceptron within the replica formalism framework, focusing on the effects of the normalization of the weights on the learning and generalization capabilities of the network. We also investigate the effects of static noise corrupting the training data and of dynamical noise acting on the weights during the training stage.
No takes yet. Share an insight, caveat, or question.
José F. Fontanari (1993) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: