During the last few years, (bottleneck) linear neural network architectures have received considerable amounts of interest due to their importance in feature extraction. Suppose that an n-dimensional random vector x is to be compressed into a p-dimensional vector y = c(x), where p < n, in a way that relative to some performance criterion, y contains as much information about x as possible. If t...

This paper considers the inversion of ill-posed linear operators. To regularise the problem the solution is enforced to lie in a non-convex subset. Theoretical properties for the stable inversion are derived and an iterative algorithm akin to the projected Landweber algorithm is studied. This work extends recent progress made on the efficient inversion of finite dimensional linear systems under...

We study the statistics of optical data transmission in a noisy nonlinear fiber channel with a weak dispersion management and zero average dispersion. Applying path integral methods we have found exactly the probability density functions of channel output both for a non-linear noisy channel and for a linear channel with additive and multiplicative noise. We have obtained analytically a lower bo...

Metacomputing is a method of using the GRID, which originated in the US and quickly was also picked up by European and Japanese researchers where a number of challenging projects were aiming at the exploitation of such distributed resources. Especially the GLOBUS project (The globus project: a status report, Proceedings IPPS/SPDP’98 Heterogeneous Computing Workshop, 1998, pp. 4–18) has contribu...

in this study, application of adaptive neuro-fuzzy inference system (anfis) in forecasting three perspectives (1, 2, and 4 years) ahead of iran’s agricultural products export was compared with arima as the most common econometrics linear forecasting method. for this purpose, iran’s agricultural products export revenues related to 1959-2010, and forecast performance measures such as r2, mad, and...

Gaussian process regression traditionally has three important downsides. (1) It is computationally intensive, (2) it cannot efficiently implement newly obtained measurements online, and (3) it cannot deal with stochastic (noisy) input points. In this paper we present an algorithm tackling all these three issues simultaneously. The resulting Sparse Online Noisy Input GP (SONIG) regression algori...

the rank-k numerical range has a close connection to the construction of quantum error correction code for a noisy quantum channel. for noisy quantum channel, a quantum error correcting code of dimension k exists if and only if the associated joint rank-k numerical range is non-empty. in this paper the notion of joint rank-k numerical range is generalized and some statements of [2011, generaliz...

In this paper, we propose a data-driven reduced homogenization technique to capture diffusional phenomena in heterogeneous materials which reveal, on macroscopic level, history-dependent non-Fickian behavior. The adopted enriched-continuum formulation, the transient effects are due underlying microstructure is represented by enrichment-variables that obtained model reduction at micro-scale. min...