论文信息 - Robustness of radial basis functions

Robustness of radial basis functions

Neural networks are intended to be used in future nanoelectronics since these architectures seem to be robust against malfunctioning elements and noise. In this paper we analyze the robustness of radial basis function networks and determine upper bounds on the mean square error under noise contaminated weights and inputs.

Ulrich Rückert | Ralf Eickhoff | U. Rückert | R. Eickhoff

[1] U. Rueckert,et al. TOLERANCE OF A BINARY ASSOCIATIVE MEMORY TOWARDS STUCK-AT-FAULTS , 1991 .

[2] T. Poggio,et al. Networks and the best approximation property , 1990, Biological Cybernetics.

[3] V. Tryba,et al. Fault-tolerance of associative memories based on neural networks , 1989, Proceedings. VLSI and Computer Peripherals. COMPEURO 89.

[4] Yogesh Singh,et al. Feedforward sigmoidal networks - equicontinuity and fault-tolerance properties , 2004, IEEE Transactions on Neural Networks.

[5] J. Nazuno. Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[6] Ulrich Rückert,et al. Local cluster neural net analog VLSI design , 1998, Neurocomputing.

[7] Behzad Razavi,et al. Design of Analog CMOS Integrated Circuits , 1999 .

[8] Shlomo Geva,et al. A constructive method for multivariate function approximation by multilayer perceptrons , 1992, IEEE Trans. Neural Networks.

[9] Ulrich Rückert,et al. A VLSI friendly neural network with localised transfer functions , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10] Tomaso A. Poggio,et al. Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[11] U. Ruckert,et al. On nanoelectronic architectural challenges and solutions , 2004, 4th IEEE Conference on Nanotechnology, 2004..

[12] C. E. SHANNON,et al. A mathematical theory of communication , 1948, MOCO.