On the Effect of Analog Noise in Discrete-Time Analog Computations
Maass, W., & Orponen, P. (1998). On the Effect of Analog Noise in Discrete-Time Analog Computations. Neural Computation, 10 (5), 1071-1095. doi:10.1162/089976698300017359
Published inNeural Computation
© 1998 Massachusetts Institute of Technology
We introduce a model for analog computation with discrete time in the presence of analog noise that is flexible enough to cover the most important concrete cases, such as noisy analog neural nets and networks of spiking neurons. This model subsumes the classical model for digital computation in the presence of noise. We show that the presence of arbitrarily small amounts of analog noise reduces the power of analog computational models to that of finite automata, and we also prove a new type of upper bound for the VC-dimension of computational models with analog noise.
NB.Published also in Advances in Neural Information Processing Systems 9 edited by M.C. Mozer and M.I. Jordan and T. Petsche, from the conference, "Neural Information Processing Systems 1996 (NIPS 1996), MIT Press. ISSN 1049-5258; ISBN 0-262-10065-7