We report on simultaneous recordings from cells in all layers of visual cortex and models developed to capture the higher order structure of population spiking activity. Specifically, we use Ising, Restricted Boltzmann Machine (RBM) and semi-Restricted Boltzmann Machine (sRBM) models to reveal laminar patterns of activity. While the Ising model describes only pairwise couplings, the RBM and sRB...

The use of Support Vector Machines (SVMs) for speaker verification has become increasingly popular. To handle the dynamic nature of the speech utterances, many SVM-based systems use dynamic kernels. Many of these kernels can be placed into two classes, parametric kernels, where the feature-space consists of parameters from the utterance-dependent model, and derivative kernels, where the derivat...

Dialect differences within a given language represent major challenges for sustained speech system performance. For speech recognition, little if any knowledge exists on differences between dialects (e.g. vocabulary, grammar, prosody, etc.). Effective dialect classification can contribute to improved ASR, speaker ID, and spoken document retrieval. This study, presents an approach to establish a...

In a previous work, we introduced the use of log-likelihood ratios of phone posterior probabilities, called Phone LogLikelihood Ratios (PLLR) as features for language recognition under an iVector-based approach, yielding high performance and promising results. However, the high dimensionality of the PLLR feature vectors (with regard to MFCC/SDC features) results in comparatively higher computat...

The availability of contiguous and non-contiguous multiword lexical units (MWUs) in Natural Language Processing (NLP) lexica enhances parsing precision, helps attachment decisions, improves indexing in information retrieval (IR) systems, reinforces information extraction (IE) and text mining, among other applications. Unfortunately, their acquisition has long been a significant problem in NLP, ...

In this contribution we present an algorithm for estimating some parameters of offset in the case of incomplete data. This estimation cannot be performed directly with an EM or SEM method because the density of local extrema in the likelihood map grows exponentially with the number of observations and because the SEM method provides a monotonic sequence of estimates so that bad initialization c...

Pseudo-BCK algebras were introduced by G. Georgescu and A. Iorgulescu as a generalization of BCK algebras in order to give a corresponding structure to pseudo-MV algebras, since the bounded commutative BCK algebras corresponde to MV algebras. Properties of pseudo-BCK algebras and their connections with other fuzzy structures were established by A. Iorgulescu and J. Kühr. The aim of this paper i...

Pseudo-hoops are algebraic structures introduced in [1, 2] by B. Bosbach under the name of complementary semigroups. This is a formalization of the paper [4]. Following [4] we prove some properties of pseudo-hoops and we define the basic concepts of filter and normal filter. The lattice of normal filters is isomorphic with the lattice of congruences of a pseudo-hoop. We also study some importan...

In this paper, we introduce the concept of interval pseudo-homegeneous uninorms. We extend the concept of pseudo-homogeneity of specific functions for interval pseudo-homogeneous functions. It is studied two cases of interval pseudo-homogeneous uninorms, that is, interval pseudo-homogeneous tnorms and interval pseudo-homogeneous t-conorms. It is proved a form of interval pseudo-homogeneous t-no...

Based on the theory of a falling shadow which was first formulated by Wang [15], a theoretical approach of the pseudo ideal structure in pseudo d-algebras is established. Several properties are investigated, and relations among a falling pseudo d-subalgebra, a falling pseudo BCK-ideal and a falling pseudo d-ideal are discussed. A characterization of a falling pseudo d-ideal is provided. Conditi...