Ensemble Learning of Linear Perceptrons: On-Line Learning Theory

DOI Web Site Web Site BIBCODE 16 Citations 16 References
  • Hara Kazuyuki
    Tokyo Metropolitan College of Technology
  • Okada Masato
    Graduate School of Frontier Sciences, The University of Tokyo Laboratory for Mathematical Neuroscience, Brain Science Institute, RIKEN Intelligent Corporation and Control, PRESTO, Japan Science and Technology Agency

Search this article

Abstract

We analyze ensemble learning including the noisy case where teacher or student noise is present. Linear perceptrons are used as teacher and student. First, we analyze the homogeneous correlation of initial weight vectors. The generalization error consists of two parts: the first term depends on the number of perceptrons K and is proportional to 1⁄K, the second does not depend on K in the first case. In the inhomogeneous correlation of initial weight vectors case, the weighted average could be optimized to minimize the generalization error. We found that the optimal weights do not depend on time without student noise, while the optimal weights depend on time and become 1⁄K with student noise.

Journal

Citations (16)*help

See more

References(16)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top