论文信息 - Investigating feedforward neural networks with respect to the rejection of spurious patterns

Investigating feedforward neural networks with respect to the rejection of spurious patterns

The reliability of feedforward neural networks with respect to the rejection of patterns not belonging to the defined training classes is investigated. It is shown how networks with different activation functions and propagation rules construct the decision regions in the pattern space and, therefore, affect the network's performance in dealing with spurious information. A modification to the standard MLP structure is described to enhance its reliability in this respect.

[1] Michael R. W. Dawson,et al. Modifying the Generalized Delta Rule to Train Networks of Non-monotonic Processors for Pattern Classification , 1992 .

[2] D. Broomhead,et al. Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[3] Stephen M. Omohundro,et al. Geometric learning algorithms , 1990 .

[4] A. Linden,et al. Inversion of multilayer nets , 1989, International 1989 Joint Conference on Neural Networks.

[5] Germano C. Vasconcelos,et al. Enhanced reliability of multilayer perceptron networks through controlled pattern rejection , 1993 .

[6] R.P. Lippmann,et al. Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[7] David S. Broomhead,et al. Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[8] Yuchun Lee,et al. Handwritten Digit Recognition Using K Nearest-Neighbor, Radial-Basis Function, and Backpropagation Neural Networks , 1991, Neural Computation.

[9] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[10] Y. Lee. Handwritten digit recognition using k nearest neighbour radial-basis function, and backpropagation , 1991 .