Answers are grounded in this paper and cite their sources.
We developed a parallel strategy for learning optimally specific realizable rules by perceptrons, in an online learning scenario. Our result is a generalization of the Caticha–Kinouchi (CK) algorithm developed for learning a perceptron with a synaptic vector drawn from a uniform distribution over the N -dimensional sphere, so called the typical case. Our method outperforms the CK algorithm in almost all possible situations, failing only in a denumerable set of cases. The algorithm is optimal in the sense that it saturates Bayesian bounds when it succeeds.
No takes yet. Share an insight, caveat, or question.
Juan Pablo Neirotti (2010) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: