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.
|Number of pages||1|
|Journal||Journal of Physics A: Mathematical and Theoretical|
|Publication status||Published - 26 Mar 2010|
Bibliographical note© 2010 IOP Publishing Ltd.
- realizable rules
- Caticha–Kinouchi algorithm
- synaptic vector
- N-dimensional sphere
- Bayesian bounds