Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i.e., updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.

• 社団法人電子情報通信学会の論文
• 1998-01-25

著者

• Ohmameuda Toshiaki

  The Faculty Of Engineering Chiba University

• Kaneko Keiichi

  The Faculty Of Engineering Chiba University

• HAMMAD Nait

  Graduate School of Science and Technology, Chiba University

• ITO Hideo

  The Faculty of Engineering, Chiba University

• Hammad Nait

  Graduate School Of Science And Technology Chiba University

• Ito Hideo

  The Faculty Of Engineering Chiba University

• Ito Hideo

  The Faculty Of Engineering Chiba Unicersity

関連論文

• Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks
• An Algorithm for Node-to-Set Disjoint Paths Problem in Bi-Rotator Graphs(Parallel/Distributed Algorithms, Parallel/Distributed Computing and Networking)
• Concurrent Core Testing for SOC Using Merged Test Set and Scan Tree(Dependable Computing)
• On the Activation Function and Fault Tolerance in Feedforward Neural Networks

スポンサーリンク