This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
papers:bottou-murata-2002 [2006/04/12 19:14] 127.0.0.1 (old revision restored) |
papers:bottou-murata-2002 [2006/04/20 11:04] (current) leonb |
||
---|---|---|---|
Line 1: | Line 1: | ||
===== Stochastic Approximations and Efficient Learning ===== | ===== Stochastic Approximations and Efficient Learning ===== | ||
+ | // | ||
+ | The analysis of online algorithms is much more difficult than that of | ||
+ | ordinary optimization algorithms. | ||
+ | processing (Widrow and Stearns, 1985) motivated the creation of | ||
+ | sophisticated mathematical tools known as {\em stochastic | ||
+ | approximations} (Ljung and Soderstrom, 1983; Benveniste, Metivier and Priouret, 1990) | ||
+ | [...] | ||
+ | The first section describes and illustrates a general framework for | ||
+ | neural network learning algorithms based on stochastic gradient | ||
+ | descent. | ||
+ | describing the //final phase// | ||
+ | conceptual aspects of the //search phase// and comments some of the | ||
+ | newest results. | ||
<box 99% orange> | <box 99% orange> | ||
- | Léon Bottou and Noboru Murata: Stochastic Approximations and Efficient Learning, | + | Léon Bottou and Noboru Murata: |
[[http:// | [[http:// |