Saad, D. and Solla, S. A. (1995). Online learning in soft committee machines.  Home/Search Document Not in Database Summary APS Related Articles Check |
This paper is cited in the following contexts:
Online Learning From Finite Training Sets - Barber, Sollich (1998) (2 citations) (Correct)
....Hertz (1992) for a scenario very similar to the (linear) one we consider below. Their j 0 offline calculation will serve as a baseline for our work. For non linear networks and finite j, progress has been made in particular for so called soft committee machine network architectures (see, e.g. Saad and Solla, 1995, Biehl and Schwarze, 1995) but only for the case of infinite training sets. Finite training sets present a significant analytical difficulty as successive weight updates are correlated, giving rise to highly non trivial generalization dynamics. This chapter is split into two main sections. In ....
....our analysis to nonlinear networks. The particular model we choose to study is the soft committee machine, which is capable of representing a rich variety of input output mappings. Its online learning dynamics has been studied comprehensively for infinite training sets(Biehl and Schwarze, 1995; Saad and Solla, 1995). In order to carry out our analysis, we adapt tools originally developed in the statistical mechanics literature which have found application, for example, in the study of Hopfield network dynamics (Coolen et al. 1996) 3.1 Model and Outline of Calculation For an N dimensional input vector x, ....
[Article contains additional citation context not shown here]
Saad, D. and Solla, S. A. (1995). Online learning in soft committee machines.
Online Learning From Finite Training Sets and Robustness to.. - Sollich, Barber (1998) (2 citations) (Correct)
....sets was provided by Krogh and Hertz (1992) for a scenario very similar to the one we consider below. Their j 0 offline calculation will serve as a baseline for our work. For finite j, progress has been made in particular for so called soft committee machine network architectures (see, e.g. Saad and Solla, 1995; Biehl and Schwarze, 1995) but only for the case of infinite training sets. In this paper, we give an exact analysis of online learning in a simple model system. Our aim is twofold: 1) to assess how the combination of non infinitesimal learning rates j and finite training sets (containing ff ....
Saad, D. and Solla, S. A. (1995). Online learning in soft committee machines. Physical Review E, 52:4225.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC