A Self-Organizing Map (SOM or Kohonen Map) is a method of mapping vectors of an n-dimensional space V into elements of a lower-dimensional subspace A having a discretized structure consisting of a lattice of so-called neurons, objects associated with vectors of the space V . We denote the with r ∈ A elements of A and with wr ∈ V their associated vectors. The SOM algorithm begins by assigning ra...

In this work, we propose a continuous-domain stochastic model that can be applied to image data. This model is autoregressive, and accounts for Gaussian-type as well as for non-Gaussian-type innovations. In order to estimate the corresponding parameters from the data, we introduce two possible error criteria; namely, Gaussian maximum-likelihood, and least-squares autocorrelation fit. Exploiting...

We give a general formulation of a non-Gaussian conditional linear AR(1) model subsuming most of the non-Gaussian AR(1) models that have appeared in the literature. We derive some general results giving properties for the stationary process mean, variance and correlation structure, and conditions for stationarity. These results highlight similarities and differences with the Gaussian AR(1) mode...

This paper describes a system for indexing acoustic feature vectors for large-scale speaker search using random projections. Given one or more target feature vectors, large-scale speaker search enables returning similar vectors (in a nearest-neighbors fashion) in sublinear time. The speaker feature space is comprised of i-vectors, derived from Gaussian Mixture Model supervectors. The index and ...

The processing of noise-corrupted signals is a common problem in signal processing applications. In most of the cases, it is assumed that the additive noise is white Gaussian and that the constant noise variance is either available or can be easily measured. However, this may not be the case in practical situations. We present a new approach to additive white Gaussian noise variance estimation....

Rapid developments of time series models and methods addressing volatility in computational finance and econometrics have been recently reported in the financial literature. The non-linear volatility theory either extends and complements existing time series methodology by introducing more general structures or provides an alternative framework (see Abraham and Thavaneswaran [B. Abraham, A. Tha...

in this paper, we deal with the problem of adaptive coherent signal detection in gaussian interference (clutter plus noise) for surveillance pulse radars. some of the adaptive radar detectors exploit the ar model for clutter. most of these detectors have been obtained using the glr test. this test relies on the maximum likelihood estimation whose accuracy depends on the number of data. whereas,...

Abstract—This paper investigates the behaviour of the spectrum of generally correlated Gaussian random matrices whose columns are zero-mean independent vectors but have different correlations, under the specific regime where the number of their columns and that of their rows grow at infinity with the same pace. This work is, in particular, motivated by applications from statistical signal proce...

A model of quantum noisy channel with input encoding by a classical random vector is described. An equation of optimality is derived to determine a complete set of wave functions describing quantum decodings based on quasi-measurements maximizing the classical amount of transmitted information. A solution of this equation is found for the Gaussian multimode case with input Gaussian distribution...