Energy Function based on Restrictions for Supervised Learning on Feedforward Networks

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper we present the construction and usage of an energy function for supervised learning on feedforward networks, based on restrictions. We focus on the mathematical deductions of the energy function, based on the Lyapunov (also called infinite) norm, from error minimization procedures. We will show how the movement equations derived from this energy function improve the learning and generalization capacity of the neural tool in the case of stock exchange (SE) prediction, in the sense of time-series (TS) prediction. We will also show some comparative results of our method and the classical backpropagation (BP) method, obtained by means of the T (Theill) test and the correlation computation. The verification of the proposed energy function is done through computer simulation.

• 一般社団法人情報処理学会の論文
• 1999-02-15

著者

• Okamoto Toshio

  Graduate School Of Information Systems University Of Electro-communications

• Okamoto T

  Graduate School Of Information Systems University Of Electro-communications

• Cristea A

  Uec Tokyo Jpn

• Cristea Alexandra

  Graduate School of Information Systems, University of Electro-Communication

• Okamoto Toshio

  Graduate School Of Information Systems The University Of Electro-communications

関連論文

• An Intelligent Programming Supporting Environment Based on Agent Model (Special Issue on Educational System using Multimedia and Communication Technology)
• The Current Situations and Future Directions of Intelligent CAI Research/Development (Special Issue on Intelligent CAI and Hypermedia)
• Energy Function based on Restrictions for Supervised Learning on Feedforward Networks
• The Integrated e-Learning System and its Practice
• The Integrated e-Learning System and its Practice
• The Distance Ecological Model to Sopport Self/Collaborative Learning in the Internet Environment
• The Distance Ecological Model to Support Self/Collaborative Learning in the Internet Environment
• Cognitive-oriented Web-based Materials Design for Teaching Academic English
• Student Modelling for Procedural Problem Solving (Special Issue on Intelligent CAI and Hypermedia)
• WeCo Design for Neural Networks
• The Network Discussion Supporting System Embedded Computer Coordinator at the Distributed Places
• e-Learning in Lithuania : trends, initiatives and achievements

もっと見る 閉じる

スポンサーリンク