A Novel Learning Algorithm Which Makes Multilayer Neural Networks Multiple-Weight-Fault Tolerant(Dependable Systems)(<Special Issue>Dependable Computing)
スポンサーリンク
概要
- 論文の詳細を見る
We propose an efficient algorithm for making multi-layered neural networks (MLN) fault-tolerant to all multiple weight faults in a multi-dimensional interval by injecting intentionally two extreme multi-dimensional values in the interval into the weights of the selected multiple links in a learning phase. The degree of fault-tolerance to a multiple weight fault is measured by the number of essential multiple links. First, we analytically discuss how to choose effectively the multiple links to be injected, and present a learning algorithm for making MLNs fault tolerant to all multiple (I.e., simultaneous) faults in the interval defined by two multi-dimensional extreme points. Then it is proved that after the learning algorithm successfully finishes, MLNs become fault tolerant to all multiple faults in the interval. It is also shown that the time in a weight modification cycle depends little on multiplicity of faults k for small k. These are confirmed by simulation.
- 2003-12-01
著者
-
Takanami Itsuo
Ichinoseki National College Of Technology
-
OYAMA Yasuhiro
Digital Culture Technology Co.
関連論文
- A Novel Learning Algorithm Which Makes Multilayer Neural Networks Multiple-Weight-Fault Tolerant(Dependable Systems)(Dependable Computing)
- Self-Reconfiguring of 1 1/2-Track-Switch Mesh Arrays with Spares on One Row and One Column by Simple Built-in Circuit(Dependable Computing)
- An implementation of a fault-tolerant 2D systolic array on an FPGA and its evaluation (ディペンダブルコンピューティング)
- An Efficiently Self-Reconstructing Array System Using E-11/2-Track Switches(Fault Tolerance)
- A System for Efficiently Self-Reconstructing 11/2-Track Switch Torus Arrays
- A Graph-Theoretic Approach to Minimizing the Number of Dangerous Processors in Fault-Tolerant Mesh-Connected Processor Arrays(Special Issue on Function Integrated Information Systems)
- An FPGA Implementation of a Self-Reconfigurable System for the 1 1/2 Track-Switch 2-D Mesh Array with PE Faults