ISBN : 978-1-4673-5306-9International audienceThe associative Hopfield memory is a form of recurrent Artificial Neural Network (ANN) that can be used in applications such as pattern recognition, noise removal, information retrieval, and combinatorial optimization problems. In general, ANNs are considered as intrinsically fault-tolerant. A study of the capability of this algorithm to tolerate transient faults such as bit-flips provoked by the radiation environment is presented. Two software versions of the Hopfield Neural Network (HNN), one original and one fault-tolerant were implemented and executed by a LEON3 processor. Experimental results show the efficiency of the adopted strategy to tolerate faults that were injected at hardware level
The sensitivity to faults induced by radiation of an artificial neural network intended to be used i...
Wide attention was recently given to the problem of fault-tolerance in neural networks; while most a...
International audienceThis paper investigates the tolerance of Artificial Neural Networks with respe...
International audienceThis letter presents an FPGA implementation of a fault-tolerant Hopfield Neura...
This letter presents an FPGA implementation of a fault-tolerant Hopfield NeuralNetwork (HNN). The ro...
In this paper we investigate the robustness of Artificial Neural Networks when encountering transien...
This thesis has examined the resilience of artificial neural networks to the effect of faults. In pa...
In this work, Hopfield Artificial Neural Network's performance in faults diagnostic in industrial pr...
This paper investigates the fault tolerance characteristics of time continuous recurrent artificial ...
The use of neural networks in critical applications necessitates that they continue to perform their...
Ph.D. ThesisAvailable from British Library Document Supply Centre- DSC:9120.156(YU-YCST--92/10) / BL...
This article is devoted to the issue of pattern recognition using neural network technologies. In pa...
I experimented with Hopfield networks in the context of a voice-based, query-answering system. Hopfi...
AbstractIn this paper, the domain of attraction of memory patterns and the exponential convergence r...
A method is proposed to estimate the fault tolerance of feedforward Artificial Neural Nets (ANNs) an...
The sensitivity to faults induced by radiation of an artificial neural network intended to be used i...
Wide attention was recently given to the problem of fault-tolerance in neural networks; while most a...
International audienceThis paper investigates the tolerance of Artificial Neural Networks with respe...
International audienceThis letter presents an FPGA implementation of a fault-tolerant Hopfield Neura...
This letter presents an FPGA implementation of a fault-tolerant Hopfield NeuralNetwork (HNN). The ro...
In this paper we investigate the robustness of Artificial Neural Networks when encountering transien...
This thesis has examined the resilience of artificial neural networks to the effect of faults. In pa...
In this work, Hopfield Artificial Neural Network's performance in faults diagnostic in industrial pr...
This paper investigates the fault tolerance characteristics of time continuous recurrent artificial ...
The use of neural networks in critical applications necessitates that they continue to perform their...
Ph.D. ThesisAvailable from British Library Document Supply Centre- DSC:9120.156(YU-YCST--92/10) / BL...
This article is devoted to the issue of pattern recognition using neural network technologies. In pa...
I experimented with Hopfield networks in the context of a voice-based, query-answering system. Hopfi...
AbstractIn this paper, the domain of attraction of memory patterns and the exponential convergence r...
A method is proposed to estimate the fault tolerance of feedforward Artificial Neural Nets (ANNs) an...
The sensitivity to faults induced by radiation of an artificial neural network intended to be used i...
Wide attention was recently given to the problem of fault-tolerance in neural networks; while most a...
International audienceThis paper investigates the tolerance of Artificial Neural Networks with respe...