Portal de Periódicos da CAPES

On-line Learning and Stochastic Approximations

1999; Cambridge University Press; Linguagem: Inglês

10.1017/cbo9780511569920.003

Léon Bottou,

Neural Networks and Applications

The convergence of online learning algorithms is analyzed using the tools of the stochastic approximation theory, and proved under very weak conditions. A general framework for online learning algorithms is first presented. This framework encompasses the most common online learning algorithms in use today, as illustrated by several examples. The stochastic approximation theory then provides general results describing the convergence of all these learning algorithms at once.