Results 1  10
of
3,422
The neural basis of cognitive development: A constructivist manifesto
 Behavioral and Brain Sciences
, 1997
"... Quartz, S. & Sejnowski, T.J. (1997). The neural basis of cognitive development: A constructivist manifesto. ..."
Abstract

Cited by 188 (2 self)
 Add to MetaCart
Quartz, S. & Sejnowski, T.J. (1997). The neural basis of cognitive development: A constructivist manifesto.
Probable networks and plausible predictions   a review of practical Bayesian methods for supervised neural networks
, 1995
"... Bayesian probabilily theory provides a unifying framework for dara modelling. In this framework the overall aims are to find models that are wellmatched to, the &a, and to use &se models to make optimal predictions. Neural network laming is interpreted as an inference of the most probable ..."
Abstract

Cited by 179 (6 self)
 Add to MetaCart
Bayesian probabilily theory provides a unifying framework for dara modelling. In this framework the overall aims are to find models that are wellmatched to, the &a, and to use &se models to make optimal predictions. Neural network laming is interpreted as an inference of the most probable parameters for Ihe model, given the training data The search in model space (i.e., the space of architectures, noise models, preprocessings, regularizes and weight decay constants) can then also be treated as an inference problem, in which we infer the relative probability of alternative models, given the data. This review describes practical techniques based on Gaussian approximations for implementation of these powerful methods for controlling, comparing and using adaptive networks.
Bayesian Methods for Adaptive Models
, 1992
"... The Bayesian framework for model comparison and regularisation is demonstrated by studying interpolation and classification problems modelled with both linear and nonlinear models. This framework quantitatively embodies `Occam's razor'. Overcomplex and underregularised models are automa ..."
Abstract

Cited by 176 (2 self)
 Add to MetaCart
The Bayesian framework for model comparison and regularisation is demonstrated by studying interpolation and classification problems modelled with both linear and nonlinear models. This framework quantitatively embodies `Occam's razor'. Overcomplex and underregularised models are automatically inferred to be less probable, even though their flexibility allows them to fit the data better. When applied to `neural networks', the Bayesian framework makes possible (1) objective comparison of solutions using alternative network architectures; (2) objective stopping rules for network pruning or growing procedures; (3) objective choice of type of weight decay terms (or regularisers); (4) online techniques for optimising weight decay (or regularisation constant) magnitude; (5) a measure of the effective number of welldetermined parameters in a model; (6) quantified estimates of the error bars on network parameters and on network output. In the case of classification models, it is sho...
A spectral clustering approach to finding communities in graphs
 In SIAM International Conference on Data Mining
, 2005
"... Clustering nodes in a graph is a useful general technique in data mining of large network data sets. In this context, Newman and Girvan [9] recently proposed an objective function for graph clustering called the Q function which allows automatic selection of the number of clusters. Empirically, high ..."
Abstract

Cited by 166 (0 self)
 Add to MetaCart
Clustering nodes in a graph is a useful general technique in data mining of large network data sets. In this context, Newman and Girvan [9] recently proposed an objective function for graph clustering called the Q function which allows automatic selection of the number of clusters. Empirically, higher values of the Q function have been shown to correlate well with good graph clusterings. In this paper we show how optimizing the Q function can be reformulated as a spectral relaxation problem and propose two new spectral clustering algorithms that seek to maximize Q. Experimental results indicate that the new algorithms are efficient and effective at finding both good clusterings and the appropriate number of clusters across a variety of realworld graph data sets. In addition, the spectral algorithms are much faster for large sparse graphs, scaling roughly linearly with the number of nodes n in the graph, compared to O(n 2) for previous clustering algorithms using the Q function. 1
DAOUDI M.: Enhancing 3D mesh topological skeletons with discrete contour constrictions. The Visual Computer 24
, 2008
"... HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte p ..."
Abstract

Cited by 10 (5 self)
 Add to MetaCart
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
THE IMPACT OF FINANCIAL AND NONFINANCIAL MEASURES ON BANKS ’ FINANCIAL STRENGTH RATINGS: THE CASE OF THE MIDDLE EAST
"... Mostafa Sayed Abdallah ..."
A Method for Learning from Hints Yaser s. AbuMostafa
"... We address the problem of learning an unknown function by pu tting together several pieces of information (hints) that we know about the function. We introduce a method that generalizes learning from examples to learning from hints. A canonical representation of hints is defined and illustrated fo ..."
Abstract
 Add to MetaCart
We address the problem of learning an unknown function by pu tting together several pieces of information (hints) that we know about the function. We introduce a method that generalizes learning from examples to learning from hints. A canonical representation of hints is defined and illustrated for new types of hints. All the hints are represented to the learning process by examples, and examples of the function are treated on equal footing with the rest of the hints. During learning, examples from different hints are selected for processing according to a given schedule. We present two types of schedules; fixed schedules that specify the relative emphasis of each hint, and adaptive schedules that are based on how well each hint has been learned so far. Our learning method is compatible with any descent technique that we may choose to use. 1
OPTIMAL DISTRIBUTION OF ACTIVE POWERS USING LINEAR PROGRAMMING WITH LOSSES COST MINIMIZATION *Ahmed ALLALI, **Hamid BOUZEBOUDJA, ***Laouer MOHAMED, ****Mostafa RAHLI,
"... This paper deals with application of linear programming techniques to achieve a mixed economic distribution of the active powers (production cost of active power and cost of the losses of transmissions) in an electric power. Performance indexes related to energy production are nonlinear. Newton met ..."
Abstract
 Add to MetaCart
This paper deals with application of linear programming techniques to achieve a mixed economic distribution of the active powers (production cost of active power and cost of the losses of transmissions) in an electric power. Performance indexes related to energy production are nonlinear. Newton method is used for linearising these cost functions around an operating point prior to their minimisation. In the first, the problem is solved by considering the fuel performance indexes only while maintaining transmission losses constant. In the second, we have considered transmission losses and production costs at the same time. We will also consider that the active losses are a function of the generated active powers and hence the coefficient of this function may be calculated with the Generalised Generation Factors Distribution (GGFD) method.
el yaagoubi
"... Abstract Metabolic syndrome (MS) is regarded as a real public health problem its prevalence rises each year as well as its morbidity. It is a multi factorial disease and besides environmental factors and genetic factors also contribute to the pathogenesis of MS. In several studies the SstI (3238C&g ..."
Abstract
 Add to MetaCart
Abstract Metabolic syndrome (MS) is regarded as a real public health problem its prevalence rises each year as well as its morbidity. It is a multi factorial disease and besides environmental factors and genetic factors also contribute to the pathogenesis of MS. In several studies the SstI (3238C> G) polymorphism of APOC3 gene is associated with increased plasma concentrations of triglyceride (TG) and hypertriglyceridemia. The aim of the present study was to determine the association between polymorphism 3238C> G in APOC3, and Metabolic Syndrome in the Moroccan Population. Statistical analysis has revealed an association of polymorphism APOC3 3238C>G susceptibility with the metabolic syndrome in two models, codominant 1 [OR = 4.21 [1.6610.68], p = 0.0008] and dominant [OR = 3.83 [1.599.19] p = 0.0010]. The variant APOC3 3238G were associated with elevated TG levels (P = 0.0146) and LDLC (p = 0.0068) compared to patients with MS and controls noncarriers of this variant.
Results 1  10
of
3,422