论文信息 - A fault-value injection approach for multiple-weight-fault tolerance of MNNs

A fault-value injection approach for multiple-weight-fault tolerance of MNNs

Many studies of methods for making multilayer neural nets (MNN) fault-tolerant by injecting intentionally the snapping of a link or a noise into links in the learning process have considered fault-tolerance to link snapping. We consider fault-tolerance to the weight fault, which includes link snapping as a special case. We take a pattern recognition problem as an example. To make an MNN fault-tolerant to any single or double weight faults in a certain interval or range, we inject intentionally two extreme points of a single or double fault-values in an interval or a range during learning. By simulation, we investigate how much MNN becomes fault-tolerant to the weight faults depending on the injected ones. The degree of fault-tolerance for a n-multiple weight fault is estimated by the number of essential multiple links. An interesting result that if only two faults of the extreme points in the interval are injected, the number of the essential links becomes zero for single faults of all the weights in the interval is obtained. This means that MNN becomes fault-tolerant to any single weight faults in the interval. Expecting that the similar result for double faults will be obtained, we inject two extreme points in two-dimensional range. As expected, the number of 2-multiple essential links has become zero in the range. This means that MNN becomes fault-tolerant to any double weight faults in the range. Finally, we analyse the internal structure of MNN by the distribution of covariance between any two inputs of a neuron in the output layer.

Itsuo Takanami | Masaru Sato | Yun Ping Yang

[1] Nait Charif Hammadi,et al. Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks , 1998 .

[2] Alan F. Murray,et al. Synaptic weight noise during multilayer perceptron training: fault tolerance and training improvements , 1993, IEEE Trans. Neural Networks.

[3] Salvatore Cavalieri,et al. A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks , 1999, Neural Networks.

[4] Takehiro Ito,et al. On fault injection approaches for fault tolerance of feedforward neural networks , 1997, Proceedings Sixth Asian Test Symposium (ATS'97).

[5] Hideo Ito,et al. On the Activation Function and Fault Tolerance in Feedforward Neural Networks , 1998 .

[6] A Learning Algorithm for Fault Tolerant Feedforward Neural Networks , 1996 .

[7] Jos Nijhuis,et al. Limits to the fault-tolerance of a feedforward neural network with learning , 1990, [1990] Digest of Papers. Fault-Tolerant Computing: 20th International Symposium.

[8] Nait Charif Hammadi,et al. Fault tolerant constructive algorithm for feedforward neural networks , 1997, Proceedings Pacific Rim International Symposium on Fault-Tolerant Systems.

[9] Katsunari Shibata,et al. A self-learning digital neural network using wafer-scale LSI , 1993 .

[10] R.D. Clay,et al. Fault tolerance training improves generalization and robustness , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.