Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC

Hyeyoung Park, Noboru Murata, Shun Ichi Amari

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Natural gradient learning is known to be efficient in escaping plateau, which is a main cause of the slow learning speed of neural networks. The adaptive natural gradient learning method for practical implementation also has been developed, and its advantage in real-world problems has been confirmed. In this letter, we deal with the generalization performances of the natural gradient method. Since natural gradient learning makes parameters fit to training data quickly, the overfitting phenomenon may easily occur, which results in poor generalization performance. To solve the problem, we introduce the regularization term in natural gradient learning and propose an efficient optimizing method for the scale of regularization by using a generalized Akaike information criterion (network information criterion). We discuss the properties of the optimized regularization strength by NIC through theoretical analysis as well as computer simulations. We confirm the computational efficiency and generalization performance of the proposed method in real-world applications through computational experiments on benchmark problems.

Original languageEnglish
Pages (from-to)355-382
Number of pages28
JournalNeural Computation
Volume16
Issue number2
DOIs
Publication statusPublished - 2004 Feb 1

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Fingerprint Dive into the research topics of 'Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC'. Together they form a unique fingerprint.

  • Cite this