Title :
Fault Models for Neural Hardware
Author :
Singh, Amit Prakash ; Chandra, Pravin ; Rai, Chandra Sekhar
Author_Institution :
Sch. of Inf. Technol., Guru Gobind Singh Indraprastha Univ., Delhi, India
Abstract :
Artificial Neural Networks are inherently fault tolerant. Fault tolerance property of artificial neural networks has been investigated with reference to the hardware model of artificial neural networks. In this paper, we propose a framework for the investigation of fault tolerance properties of a hardware model of artificial neural networks. The result obtained indicates that networks obtained by training them with the resilient back propagation algorithm are not fault tolerant: more experimentation is required before a definitive statement can be made for other training algorithms, like the adaptive learning rate algorithm, the conjugate gradient based training algorithms, etc.
Keywords :
fault tolerant computing; neural nets; adaptive learning rate algorithm; artificial neural network; conjugate gradient; fault model; fault tolerance property; hardware model; neural hardware; resilient backpropagation; training algorithm; Application specific integrated circuits; Artificial neural networks; Biological neural networks; Circuit faults; Fault tolerance; Field programmable gate arrays; Multilayer perceptrons; Neural network hardware; Neurons; Parallel processing; artificial neural network; fault model;
Conference_Titel :
Advances in System Testing and Validation Lifecycle, 2009. VALID '09. First International Conference on
Conference_Location :
Porto
Print_ISBN :
978-1-4244-4862-3
Electronic_ISBN :
978-0-7695-3774-0
DOI :
10.1109/VALID.2009.32