Improving Generalization Ability through Active Learning

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we discuss the problem of active training data selection for improving the generalization capability of a neural network. We look at the learning problem from a function approximation perspective and formalize it as an inverse problem. Based on this framework, we analytically derive a method of choosing a training data set optimized with respect to the Wiener optimization criterion. The final result uses the apriori correlation information on the original function ensemble to devise an efficient sampling scheme which, when used in conjunction with the learning scheme described here, is shown to result in optimal generalization. This result is substantiated through a simulated example and a learning problem in high dimensional function space.

• 社団法人電子情報通信学会の論文
• 1999-02-25

著者

• Vijayakumar Sethu

  Information Synthesis Lab Riken Brain Science Institute

• OGAWA Hidemitsu

  Graduate School of Information Science and Engineering, Tokyo Institute of Technology

• Ogawa Hidemitsu

  Graduate School Of Information Science And Engineering Tokyo Institute Of Technology

関連論文

• Admissibility of Memorization Learning with Respect to Projection Learning in the Presence of Noise
• Partial Projection Filter for Signal Restoration in the Presence of Signal Space Noise(Image Processing and Video Processing)
• Characterization and Implementation of Partial Projection Filter in the Presence of Signal Space Noise(Image Processing and Video Processing)
• Improving Generalization Ability through Active Learning

スポンサーリンク