Search results for "embedding"

An efficient method for clustered multi-metric learning

2019

Abstract Distance metric learning, which aims at finding a distance metric that separates examples of one class from examples of the other classes, is the key to the success of many machine learning tasks. Although there has been an increasing interest in this field, learning a global distance metric is insufficient to obtain satisfactory results when dealing with heterogeneously distributed data. A simple solution to tackle this kind of data is based on kernel embedding methods. However, it quickly becomes computationally intractable as the number of examples increases. In this paper, we propose an efficient method that learns multiple local distance metrics instead of a single global one.…

Robust stability and stabilization of uncertain T-S fuzzy systems with time-varying delay: An input-output approach

2013

An input-output approach to the stability and stabilization of uncertain Takagi-Sugeno (T-S) fuzzy systems with time-varying delay is proposed in this paper. The time-varying parameter uncertainties are assumed to be norm-bounded, and the delay is intervally time varying. A novel method is employed to approximate the time-varying delay, based on which the considered system is transformed into a feedback interconnection form. The new formulation of the system is comprised of a forward subsystem with constant time delay and a feedback subsystem embedding the uncertainties. By applying the scaled small-gain theorem to the converted system, less conservative stability and stabilization criteria…

Learning with the kernel signal to noise ratio

2012

This paper presents the application of the kernel signal to noise ratio (KSNR) in the context of feature extraction to general machine learning and signal processing domains. The proposed approach maximizes the signal variance while minimizes the estimated noise variance in a reproducing kernel Hilbert space (RKHS). The KSNR can be used in any kernel method to deal with correlated (possibly non-Gaussian) noise. We illustrate the method in nonlinear regression examples, dependence estimation and causal inference, nonlinear channel equalization, and nonlinear feature extraction from high-dimensional satellite images. Results show that the proposed KSNR yields more fitted solutions and extract…

2014

This paper deals with designing the controller of LTI system based on data-driven techniques. We propose a scheme embedding a residual generator into control loop based on realization of the Youla parameterization for advanced controller design. Basic idea of the proposed scheme is constructing the residual generator by using the solution of the Luenberger equations as well as the well-established relationship between diagnosis observer (DO) and the parity vector. Besides, the core of the above idea is straightly using the process measurements to obtain the parity space based on the Subspace Identification Method (SIM), rather than establishing the system model. At last, a simulation based …

Is recursion language-specific? Evidence of recursive mechanisms in the structure of intentional action

2014

In their 2002 seminal paper Hauser, Chomsky and Fitch hypothesize that recursion is the only human-specific and language-specific mechanism of the faculty of language. While debate focused primarily on the meaning of recursion in the hypothesis and on the human-specific and syntax-specific character of recursion, the present work focuses on the claim that recursion is language-specific. We argue that there are recursive structures in the domain of motor intentionality by way of extending John R. Searle's analysis of intentional action. We then discuss evidence from cognitive science and neuroscience supporting the claim that motor-intentional recursion is language-independent and suggest so…

Aberrant arrested in maturation neuromuscular junctions in centronuclear myopathy

1994

Unusual ultrastructural changes of the nerve terminals have been found in an infant born with severe, fatal XLR form of centronuclear myopathy. Aberrant neuromuscular junctions in myotubes decorated by N-CAM were observed. The junction changes were manifested by simplification of postsynaptic membrane and paucity of secondary synaptic clefts. These resembles fetal neuromuscular junctions. The findings suggest that the expression of N-CAM by arrested myotubes may be promoted by abnormal nerve-muscle cell interactions, induced by motor endplate immaturity.

Distribution patterns in glycoconjugate expression during the development of the rat palate.

1994

The distribution of complex carbohydrate structures during the embryonic development of the rat palate was analysed by examining lectin-binding patterns in serial paraffin and cryostat sections. With few exceptions, the binding patterns showed a general increase in lectin receptors in the more developed stages of palatogenesis. High mannose oligosaccharides were especially amplified during development. Terminal fucose molecules were not expressed. In contrast, terminal sialic acid molecules were ubiquitously distributed in epithelial and mesenchymal tissues. Non-sialylated terminal N-acetylglucosamine was specifically restricted to evolving bone matrix. Before palatal fusion, quantitative b…

Prognostic indicators for squamous cell carcinoma of the oral cavity: a clinicopathologic correlation.

1997

Fifty-three patients with T1 squamous cell cancer of the floor of mouth and ventral surface of the tongue with a known clinical outcome were retrospectively analyzed and arbitrarily divided into "aggressive" and "nonaggressive" groups based on their clinical behavior. Various host and tumor factors were then evaluated in an attempt to determine whether the tumor behavior could have been predicted. The paraffin-embedded tumor specimens were evaluated for tumor differentiation, tumor thickness and tumor invasion, microvessel density, and p53 expression. In addition, a composite morphologic grading score was obtained by combining cell differentiation, nuclear polymorphism, mitosis activity, de…

Cell death and oxidative stress in gliomas.

1999

In gliomas, apoptosis and necrosis are determined by a number of promoting and inhibiting factors including oxidative cell stress mediated by nitric oxide synthases (NOS) and reduced by superoxide dismutases. Therefore, in 46 gliomas (including astrocytomas, oligodendrogliomas, oligo-astrocytomas, and glioblastomas), the relationship of apoptosis and necrosis and the expression of apoptosis-promoting (p53, bax, Fas, Fas-L) and inhibiting (bcl-2) factors as well as of different isoforms of NOS (NOSb, NOSe, NOSi) and manganese superoxide dismutase (MnSOD) were studied. Apoptosis was measured in situ by the TUNEL method while expression profiles of apoptosis-related and oxidative stress-associ…

Customer recommendation based on profile matching and customized campaigns in on-line social networks

2019

We propose a general framework for the recommendation of possible customers (users) to advertisers (e.g., brands) based on the comparison between On-Line Social Network profiles. In particular, we associate suitable categories and subcategories to both user and brand profiles in the considered On-line Social Network. When categories involve posts and comments, the comparison is based on word embedding, and this allows to take into account the similarity between the topics of particular interest for a brand and the user preferences. Furthermore, user personal information, such as age, job or genre, are used for targeting specific advertising campaigns. Results on real Facebook dataset show t…