Search results for "generalization"

showing 10 items of 250 documents

Fractional-order theory of thermoelasticicty. I: Generalization of the Fourier equation

2018

The paper deals with the generalization of Fourier-type relations in the context of fractional-order calculus. The instantaneous temperature-flux equation of the Fourier-type diffusion is generalized, introducing a self-similar, fractal-type mass clustering at the micro scale. In this setting, the resulting conduction equation at the macro scale yields a Caputo's fractional derivative with order [0,1] of temperature gradient that generalizes the Fourier conduction equation. The order of the fractional-derivative has been related to the fractal assembly of the microstructure and some preliminary observations about the thermodynamical restrictions of the coefficients and the state functions r…

Uses of trigonometryGeneralization01 natural sciences010305 fluids & plasmasScreened Poisson equationsymbols.namesakeFractional operators0103 physical sciencesFractional Fourier equationMechanics of Material010306 general physicsFourier seriesMathematicsFourier transform on finite groupsEntropy functionsHill differential equationPartial differential equationMechanical EngineeringFourier inversion theoremMathematical analysisTemperature evolutionMechanics of MaterialssymbolsFractional operatorSettore ICAR/08 - Scienza Delle CostruzioniEntropy function
researchProduct

Experimental studies on continuous speech recognition using neural architectures with “adaptive” hidden activation functions

2010

The choice of hidden non-linearity in a feed-forward multi-layer perceptron (MLP) architecture is crucial to obtain good generalization capability and better performance. Nonetheless, little attention has been paid to this aspect in the ASR field. In this work, we present some initial, yet promising, studies toward improving ASR performance by adopting hidden activation functions that can be automatically learned from the data and change shape during training. This adaptive capability is achieved through the use of orthonormal Hermite polynomials. The “adaptive” MLP is used in two neural architectures that generate phone posterior estimates, namely, a standalone configuration and a hierarch…

VocabularyArtificial neural networkbusiness.industryGeneralizationComputer sciencemedia_common.quotation_subjectSpeech recognitionPattern recognitionTIMITPerceptronField (computer science)Orthonormal basisArtificial intelligencebusinessHidden Markov modelmedia_common2010 IEEE International Conference on Acoustics, Speech and Signal Processing
researchProduct

Typically and Atypically Developing Children' Generalizations of Novel Names: the Role of Semantic Distance

2019

International audience; Children often learn the extension of novel words with a limited number of exemplars. There is evidence that the opportunity to compare stimuli is beneficial for learning and generalizing novel names in typically developing (TD) children (e.g., Gentner, 2010). However, so far,, comparison situations have not been studied in children with intellectual disabilities (ID) (Chapman & Kay-Raining Bird, 2012). This is important since they are in need of well-devised learning situations. We manipulated the role of semantic distance within training stimuli and between training and test stimuli and their influence on taxonomically-based generalization. We hypothesized more dif…

[SCCO.NEUR]Cognitive science/Neuroscience[SCCO.PSYC] Cognitive science/Psychology[SCCO.NEUR] Cognitive science/NeuroscienceNovel names learning[SCCO.PSYC]Cognitive science/Psychologyatypical childrengeneralization
researchProduct

Children’s Learning and Generalization of Novel Concepts with Comparison Designs

2022

Teaching a new word to children usually consists of the concomitant presentation of its phonological form and an example. It is then expected that they will be able, from this unique example, to generalize the new word to other entities of the same category. They must therefore understand which properties of the example are relevant to correctly generalize the new word (Murphy, 2002). The main objective of this thesis work is to better understand the learning situations of a new concept and its generalization to new stimuli. For this, investigated the comparison paradigm and how variations of the parameters of the task affect generalization.After presenting our paradigm of interest, we show…

[SHS.PSY] Humanities and Social Sciences/PsychologyExpérimentationConceptGeneralizationLearningComparisonComparaisonExperimentationApprentissageConceptsGénéralisation
researchProduct

Multi-functional Protein Clustering in PPI Networks

2008

Protein-Protein Interaction (PPI) networks contain valuable information for the isolation of groups of proteins that participate in the same biological function. Many proteins play different roles in the cell by taking part in several processes, but isolating the different processes in which a protein is involved is often a difficult task. In this paper we present a method based on a greedy local search technique to detect functional modules in PPI graphs. The approach is conceived as a generalization of the algorithm PINCoC to generate overlapping clusters of the interaction graph in input. Due to this peculiarity, multi-facets proteins are allowed to belong to different groups correspondi…

business.industryComputer scienceFunctional proteinGeneralizationA proteinPattern recognitionTask (project management)Bioinformatics network analysisLocal search (optimization)Artificial intelligenceIsolation (database systems)businessCluster analysisNetwork analysis
researchProduct

Multi-dimensional pattern matching with dimensional wildcards

1995

We introduce a new multi-dimensional pattern matching problem, which is a natural generalization of the on-line search in string matching. We are given a text matrix A[1: n1, ..., 1:n d ] of size N= n1×n2×...×n d , which we may preprocess. Then, we are given, online, an r-dimensional pattern matrix B[1:m1,...,1:m r ] of size M= m1×m2×...×m r , with 1≤r≤d. We would like to know whether B*=B*[*, 1:m1,*, ...,1: mr, *] occurs in A, where * is a dimensional wildcard such that B* is any d-dimensional matrix having size 1 × ... × m1×...1×m r ×...1 and containing the same elements as B. Notice that there might be (d/r)≤2d occurrences of B* for each position of A. We give CRCW-PRAM algorithms for pr…

business.industryGeneralizationCommentz-Walter algorithmPattern recognitionWildcard characterString searching algorithmcomputer.file_formatApproximate string matchingBinary logarithmCombinatoricsMatrix (mathematics)Artificial intelligencePattern matchingbusinesscomputerMathematics
researchProduct

A generalizability measure for program synthesis with genetic programming

2021

The generalizability of programs synthesized by genetic programming (GP) to unseen test cases is one of the main challenges of GP-based program synthesis. Recent work showed that increasing the amount of training data improves the generalizability of the programs synthesized by GP. However, generating training data is usually an expensive task as the output value for every training case must be calculated manually by the user. Therefore, this work suggests an approximation of the expected generalization ability of solution candidates found by GP. To obtain candidate solutions that all solve the training cases, but are structurally different, a GP run is not stopped after the first solution …

business.industryGeneralizationComputer scienceValue (computer science)Genetic programmingMachine learningcomputer.software_genreTask (project management)Set (abstract data type)Test caseGeneralizability theoryArtificial intelligencebusinesscomputerProgram synthesisProceedings of the Genetic and Evolutionary Computation Conference
researchProduct

Generalization of Linked Canonical Polyadic Tensor Decomposition for Group Analysis

2019

Real-world data are often linked with each other since they share some common characteristics. The mutual linking can be seen as a core driving force of group analysis. This study proposes a generalized linked canonical polyadic tensor decomposition (GLCPTD) model that is well suited to exploiting the linking nature in multi-block tensor analysis. To address GLCPTD model, an efficient algorithm based on hierarchical alternating least squa res (HALS) method is proposed, termed as GLCPTD-HALS algorithm. The proposed algorithm enables the simultaneous extraction of common components, individual components and core tensors from tensor blocks. Simulation experiments of synthetic EEG data analysi…

canonical polyadicComputer scienceGeneralizationNoise reductionlinked tensor decomposition020206 networking & telecommunications02 engineering and technologyIterative reconstructionhierarchical alternating least squares03 medical and health sciencessimultaneous extraction0302 clinical medicineGroup analysisCore (graph theory)0202 electrical engineering electronic engineering information engineeringTensor decompositionTensorAlgorithmRealization (systems)030217 neurology & neurosurgery
researchProduct

Intranasal oxytocin decreases fear generalization in males, but does not modulate discrimination threshold

2021

Background: A previously acquired fear response often spreads to perceptually or conceptually close stimuli or contexts. This process, known as fear generalization, facilitates the avoidance of danger, and dysregulations in this process play an important role in anxiety disorders. Oxytocin (OT) has been shown to modulate fear learning, yet effects on fear generalization remain unknown. Methods: We employed a randomized, placebo-controlled, double-blind, between-subject design during which healthy male participants received either intranasal OT or placebo (PLC) following fear acquisition and before fear generalization with concomitant acquisition of skin conductance responses (SCRs). Twenty-…

ehdollistuminendiscrimination thresholdoksitosiinioxytocinskin conductance responses (SCRs).ahdistuneisuushäiriötfear generalizationpelko
researchProduct

Asymptotic Hölder regularity for the ellipsoid process

2020

We obtain an asymptotic Hölder estimate for functions satisfying a dynamic programming principle arising from a so-called ellipsoid process. By the ellipsoid process we mean a generalization of the random walk where the next step in the process is taken inside a given space dependent ellipsoid. This stochastic process is related to elliptic equations in non-divergence form with bounded and measurable coefficients, and the regularity estimate is stable as the step size of the process converges to zero. The proof, which requires certain control on the distortion and the measure of the ellipsoids but not continuity assumption, is based on the coupling method.

equations in non-divergence formControl and OptimizationDynamic programming principleGeneralizationSpace (mathematics)01 natural sciencesMeasure (mathematics)local Hölder estimatespeliteoriastochastic games0101 mathematicsstokastiset prosessitMathematicsosittaisdifferentiaaliyhtälötStochastic process010102 general mathematicsMathematical analysisRandom walkEllipsoidcoupling of stochastic processes010101 applied mathematicsDistortion (mathematics)Computational Mathematicsellipsoid processControl and Systems EngineeringBounded functionESAIM: Control, Optimisation and Calculus of Variations
researchProduct