Learning networks for process identification and associative action
Using short-time correlation function measurements of an observed process as input, we show that it is possible to train a network to learn the non-linear stochastic dynamics underlying the process. Alternatively this can be formulated as a neural network with non-linear stochastic synapses, which can, after training, be used to associate actions.
Unable to display preview. Download preview PDF.
- H.Haken, Information and Self-Organization, Springer-Verlag, Berlin-Heidelberg-New York 1988Google Scholar
- L.Borland, H.Haken, Unbiased Determination of Forces Causing observed Processes, Z. Phys. B — Condensed Matter 81 (1992) 95Google Scholar
- L.Borland, H. Haken, Unbiased Estimate of Forces from Measured Correlation Functions, including the Case of Strong Multiplicative Noise, Ann. Physik 1 (1992) 452Google Scholar
- L.Borland, H. Haken, Learning the Dynamics of Two Dimensional Stochastic Markov Processes, to be published in Open Systems and Information DynamicsGoogle Scholar
- E.T. Jaynes, Phs. Rev 106 (1957) 4,620Google Scholar