A Modified Information Criterion for Automatic Model and Parameter Selection in Neural Network Learning

スポンサーリンク

概要

• 論文の詳細を見る

• This paper proposes a practical training algorithm for artificial neural networks, by which both the optimally pruned model and the optimally trained parameter for the minimum prediction error can be found simultaneously. In the proposed algorithm, the conventional information criterion is modified into a differentiable function of weight parameters, and then it is minimized while being controlled back to the conventional form. Since this method has several theoretical problems, its effectiveness is examined by computer simulations and by an application to practical ultrasonic image reconstruction.

• 社団法人電子情報通信学会の論文
• 1995-04-25

著者

• Watanabe Sumio

  Research Laboratories Of Pharmaceutical Development Eisai Co. Ltd.

• Watanabe S

  Eisai Co. Ltd. Ibaraki Jpn

• Watanabe Sumio

  Faculty of Engineering, Gifu University

関連論文

• Electrophysiologic Effects of Nitrous Oxide, a Volatile Anesthetic, in Dogs Following Myocardial Infarction in Comparison with Other Anesthetics
• Effects of Astemizole on Ventricular Activation Delay and RT Intervals in a Canine Myocardial Infarction Model
• IN VITRO AND IN VIVO EVALUATION OF A SUSTAINED RELEASE PREPARATION CONTAINING PHENYLPROPANOLAMINE HYDROCHLORIDE
• AN EXAMPLE OF PHARMACEUTICAL STUDIES ON SUSTAINED RELEASE DOSAGE DESIGN
• A Modified Information Criterion for Automatic Model and Parameter Selection in Neural Network Learning

スポンサーリンク