Complexities of feature-based learning systems, with application to reservoir computing.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

This paper studies complexity measures of reservoir systems. For this purpose, a more general model that we call a feature-based learning system, which is the composition of a feature map and of a final estimator, is studied. We study complexity measures such as growth function, VC-dimension, pseudo-dimension and Rademacher complexity. On the basis of the results, we discuss how the unadjustability of reservoirs and the linearity of readouts can affect complexity measures of the reservoir systems. Furthermore, some of the results generalize or improve the existing results.

Authors

  • Hiroki Yasumoto
    Graduate School of Informatics, Kyoto University, 36-1, Yoshida Honmachi, Sakyo-ku, Kyoto, 606-8501, Japan. Electronic address: yasumoto@sys.i.kyoto-u.ac.jp.
  • Toshiyuki Tanaka
    Graduate School of Informatics, Kyoto University, 36-1, Yoshida Honmachi, Sakyo-ku, Kyoto, 606-8501, Japan. Electronic address: tt@i.kyoto-u.ac.jp.