Asymptotic behaviour in learning from stochastic examples: one-step RSB calculation of the learning curve
Tatsuya Uezu; Yoshiyuki Kabashima; Tatsuya Uezu; Department of Physics, Nara Women's University, Nara 630, Japan; Yoshiyuki Kabashima; Department of Physics, Nara Women's University, Nara 630, Japan
Журнал:
Journal of Physics A: Mathematical and General
Дата:
1996-02-07
Аннотация:
The asymptotic learning curve of a N-dimensional stochastic learning model is calculated in the statistical mechanical framework. For the N = 1 case, Kabashima and Shinomoto (1992) gave a power law with exponent . However, this is inconsistent with the RS solution with the exponent obtained by Györgyi and Tishby (1990). We show that the one-step RSB solution is consistent with Kabashima and Shinomoto's result up to a logarithmic correction.
94.39Кб