Fast Convergent Genetic-Type Search for Multi-Layered Network (Special Section of Papers Selected from the 8th Digital Signal Processing Symymposium)

スポンサーリンク

概要

• 論文の詳細を見る

• The classical supervised learning algorithms for optimizing multi-layered feedforward neural networks, such as the original back-propagation algorithm, suffer from several weaknesses. First, they have the possibility of being trapped at local minima during learning, which may lead to failure in finding the global optimal solution. Second, the convergence rate is typically too slow even if the learning can be achieved. This paper introduces a new learning algorithm which employs a genetic-type search during the learing phase of back-propagation algorithm so that the above problems can be over-come. The basic idea is to evolve the network weights in a controlled manner so as to jump to the regions of smaller mean squared error whenever the back-propagation stops at a local minimum. By this, the local minima can always be escaped and a much faster learning with global optimal solution can be achieved. A mathematical framework on the weight evolution of the new algorithm is also presented in this paper, which gives a careful analysis on the requirements of weight evolution (or perturbation) during learning in order to achieve a better error performance in the weights between different hidden layers. Simulation results on three typical problems including XOR, -bit parity and the counting problem are described to illustrate the fast learning behaviour and the global search capability of the new algorithm in improving the performance of back-propagated network.

• 社団法人電子情報通信学会の論文
• 1994-09-25

著者

• Luk Andrew

  Department Of Electronic Engineering City Polytechnic Of Hong Kong

• Ng Sin-chun

  Department Of Electronic Engineering City Polytechnic Of Hong Kong

• Leung Shu-hung

  Department Of Electronic Engineering City Polytechnic Of Hong Kong

関連論文

• Performance Analysis of a De-correlated Modified Code Tracking Loop for Synchronous DS-CDMA System under Multiuser Environment
• Fast Convergent Genetic-Type Search for Multi-Layered Network (Special Section of Papers Selected from the 8th Digital Signal Processing Symymposium)
• Power Control for Space-Time Block Coded MIMO System with Beamforming and Imperfect Channel State Information

スポンサーリンク