Problem solving in artificial neural networks

Hampson, Steven E.

doi:10.1016/0301-0082(94)90065-5

Cited by 2 publications

(1 citation statement)

References 247 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The brain is composed of biological neural networks (BNNs) that contain billions of interconnecting neurons with the ability to perform computations. Artificial neural networks (ANNs), mathematical models that mimic BNNs, are typically built as structured node groups with activation functions and connection weights that are adjusted based on the applied learning rules (Hampson, 1991 , 1994 ; Basheer and Hajmeer, 2000 ; Krogh, 2008 ). Because of their powerful computational and learning abilities, ANNs are being used increasingly in various fields, including computation, engineering, machine learning, clinical medicine, and cognitive science (Presnell and Cohen, 1993 ; Baxt, 1995 ; Dybowski and Gant, 1995 ; Forsstrom and Dalton, 1995 ; Kamimura et al, 1996 ; Almeida, 2002 ; Lisboa, 2002 ; Rajan and Tolley, 2005 ; Lisboa and Taktak, 2006 ; Patel and Goyal, 2007 ; Hu et al, 2013 ; Street et al, 2013 ; Azimi et al, 2015 ).…”

Section: Introductionmentioning

confidence: 99%

The superior fault tolerance of artificial neural network training with a fault/noise injection-based genetic algorithm

Yuan

Wang

et al. 2016

Protein Cell

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are powerful computational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance (FT), an important property of ANNs, ensures their reliability when significant portions of a network are lost. In this paper, a fault/noise injection-based (FIB) genetic algorithm (GA) is proposed to construct fault-tolerant ANNs. The FT performance of an FIB-GA was compared with that of a common genetic algorithm, the back-propagation algorithm, and the modification of weights algorithm. The FIB-GA showed a slower fitting speed when solving the exclusive OR (XOR) problem and the overlapping classification problem, but it significantly reduced the errors in cases of single or multiple faults in ANN weights or nodes. Further analysis revealed that the fit weights showed no correlation with the fitting errors in the ANNs constructed with the FIB-GA, suggesting a relatively even distribution of the various fitting parameters. In contrast, the output weights in the training of ANNs implemented with the use the other three algorithms demonstrated a positive correlation with the errors. Our findings therefore indicate that a combination of the fault/noise injection-based method and a GA is capable of introducing FT to ANNs and imply that the distributed ANNs demonstrate superior FT performance.Electronic supplementary materialThe online version of this article (doi:10.1007/s13238-016-0302-5) contains supplementary material, which is available to authorized users.

show abstract