An improvement in weight-fault tolerance of feedforward neural networks

Proceedings of the Asian Test Symposium

Volumn , Issue , 2001, Pages 359-364

  Kamiura, Naotake ^a   Taniguchi, Yasuyuki ^a   Isokawa, Teijiro ^a   Matsui, Nobuyuki ^a  

^a UNIVERSITY OF HYOGO   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; BACKPROPAGATION; FAULT TOLERANT COMPUTER SYSTEMS; LEARNING SYSTEMS; NUMERICAL METHODS;

NEURON; STANDARD BACKPROPAGATION ALGORITHM; STUCK AT FAULTS; WEIGHT FAULT TOLERANCE;

FEEDFORWARD NEURAL NETWORKS;

EID: 0035701604     PISSN: 10817735     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Neural networks, a comprehensive foundation
2. An 11-million transistor neural network execution engine
3. Hardware-backpropagation learning of neuron MOS neural networks
4. An excellent weight-updating-linearity EEPROM synapse memory cell for self-learning neuron-MOS neural networks
5. The digineocognitron: A digital neocognitron neural network model for VLSI
6. Asynchronous VLSI neural networks using pulse stream arithmetic
7. Limits to the fault-tolerance of a feedforward neural network with learning
8. Training techniques to obtain fault-tolerant neural networks
9. Determining and improving the fault tolerance of multilayer perceptions in a pattern-recognition application
10. Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training
11. A fault tolerant multi-layer neural network model and its properties
12. A fault injection approach for multiple-weight-fault tolerance of multi-layered neural networks
13. On fault injection approaches for fault tolerance of feedforward neural networks
14. A learning algorithm for fault tolerant feedforward neural networks
15. Fault tolerant feedforward neural networks with learning algorithm based on synaptic weight limit
16. Improvement of MTTF of feedforward neural networks by applying re-learning
17. Activation function manipulation for fault tolerant feedforward neural networks