Search results for "DDE"

showing 10 items of 1858 documents

Using Hankel matrices for dynamics-based facial emotion recognition and pain detection

2015

This paper proposes a new approach to model the temporal dynamics of a sequence of facial expressions. To this purpose, a sequence of Face Image Descriptors (FID) is regarded as the output of a Linear Time Invariant (LTI) system. The temporal dynamics of such sequence of descriptors are represented by means of a Hankel matrix. The paper presents different strategies to compute dynamics-based representation of a sequence of FID, and reports classification accuracy values of the proposed representations within different standard classification frameworks. The representations have been validated in two very challenging application domains: emotion recognition and pain detection. Experiments on…

FOS: Computer and information sciencesComputer Science - Artificial IntelligenceComputer Vision and Pattern Recognition (cs.CV)Speech recognitionFeature extractionComputer Science - Computer Vision and Pattern RecognitionPainLTI system theoryComputer Science - RoboticsLinear time invariant systemRepresentation (mathematics)Hidden Markov modelMathematicsEmotionSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSequencebusiness.industryPattern recognitiondynamicsClassificationSupport vector machineArtificial Intelligence (cs.AI)Face (geometry)Artificial intelligencebusinessRobotics (cs.RO)Hankel matrix2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
researchProduct

ASR performance prediction on unseen broadcast programs using convolutional neural networks

2018

In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably …

FOS: Computer and information sciencesComputer Science - Computation and LanguageComputer scienceSpeech recognitionFeature extractionInformationSystems_INFORMATIONSTORAGEANDRETRIEVAL02 engineering and technology010501 environmental sciences01 natural sciencesConvolutional neural network[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]Task (project management)[INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL]0202 electrical engineering electronic engineering information engineeringTask analysisPerformance prediction020201 artificial intelligence & image processingMel-frequency cepstrumTranscription (software)Hidden Markov modelComputation and Language (cs.CL)ComputingMilieux_MISCELLANEOUS0105 earth and related environmental sciences
researchProduct

Symmetry meets AI

2021

We explore whether Neural Networks (NNs) can {\it discover} the presence of symmetries as they learn to perform a task. For this, we train hundreds of NNs on a {\it decoy task} based on well-controlled Physics templates, where no information on symmetry is provided. We use the output from the last hidden layer of all these NNs, projected to fewer dimensions, as the input for a symmetry classification task, and show that information on symmetry had indeed been identified by the original NN without guidance. As an interdisciplinary application of this procedure, we identify the presence and level of symmetry in artistic paintings from different styles such as those of Picasso, Pollock and Van…

FOS: Computer and information sciencesComputer Science - Machine Learning0303 health sciencesTheoretical computer scienceArtificial neural networkComputer Vision and Pattern Recognition (cs.CV)PhysicsQC1-999Computer Science - Computer Vision and Pattern RecognitionFOS: Physical sciencesGeneral Physics and Astronomy01 natural sciencesMachine Learning (cs.LG)Task (project management)High Energy Physics - Phenomenology03 medical and health sciencesHigh Energy Physics - Phenomenology (hep-ph)0103 physical sciencesHomogeneous spacePICASSOHidden layerSymmetry (geometry)010306 general physics030304 developmental biologySciPost Physics
researchProduct

Quantum autoencoders via quantum adders with genetic algorithms

2017

The quantum autoencoder is a recent paradigm in the field of quantum machine learning, which may enable an enhanced use of resources in quantum technologies. To this end, quantum neural networks with less nodes in the inner than in the outer layers were considered. Here, we propose a useful connection between quantum autoencoders and quantum adders, which approximately add two unknown quantum states supported in different quantum systems. Specifically, this link allows us to employ optimized approximate quantum adders, obtained with genetic algorithms, for the implementation of quantum autoencoders for a variety of initial states. Furthermore, we can also directly optimize the quantum autoe…

FOS: Computer and information sciencesComputer Science::Machine Learning0301 basic medicineComputer Science - Machine LearningAdderPhysics and Astronomy (miscellaneous)Quantum machine learningField (physics)Computer scienceMaterials Science (miscellaneous)Computer Science::Neural and Evolutionary ComputationFOS: Physical sciencesData_CODINGANDINFORMATIONTHEORYTopology01 natural sciencesMachine Learning (cs.LG)Statistics::Machine Learning03 medical and health sciencesQuantum state0103 physical sciencesNeural and Evolutionary Computing (cs.NE)Electrical and Electronic Engineering010306 general physicsQuantumQuantum PhysicsArtificial neural networkComputer Science - Neural and Evolutionary ComputingTheoryofComputation_GENERALAutoencoderAtomic and Molecular Physics and OpticsQuantum technology030104 developmental biologyComputerSystemsOrganization_MISCELLANEOUSQuantum Physics (quant-ph)
researchProduct

Cyclic Complexity of Words

2014

We introduce and study a complexity function on words $c_x(n),$ called \emph{cyclic complexity}, which counts the number of conjugacy classes of factors of length $n$ of an infinite word $x.$ We extend the well-known Morse-Hedlund theorem to the setting of cyclic complexity by showing that a word is ultimately periodic if and only if it has bounded cyclic complexity. Unlike most complexity functions, cyclic complexity distinguishes between Sturmian words of different slopes. We prove that if $x$ is a Sturmian word and $y$ is a word having the same cyclic complexity of $x,$ then up to renaming letters, $x$ and $y$ have the same set of factors. In particular, $y$ is also Sturmian of slope equ…

FOS: Computer and information sciencesDiscrete Mathematics (cs.DM)Formal Languages and Automata Theory (cs.FL)Computer Science - Formal Languages and Automata Theory0102 computer and information sciences68R15Characterization (mathematics)[INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM]01 natural sciencesTheoretical Computer ScienceCombinatoricsConjugacy class[INFO.INFO-FL]Computer Science [cs]/Formal Languages and Automata Theory [cs.FL][MATH.MATH-CO]Mathematics [math]/Combinatorics [math.CO]FOS: MathematicsDiscrete Mathematics and CombinatoricsMathematics - Combinatorics0101 mathematics[MATH]Mathematics [math]Discrete Mathematics and CombinatoricMathematicsDiscrete mathematicsFactor complexity010102 general mathematicsSturmian wordSturmian wordComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Sturmian wordsCyclic complexity factor complexity Sturmian words minimal forbidden factorInfimum and supremumToeplitz matrixComputational Theory and Mathematics010201 computation theory & mathematicsCyclic complexityBounded functionComplexity functionCombinatorics (math.CO)Word (group theory)Computer Science::Formal Languages and Automata TheoryComputer Science - Discrete Mathematics
researchProduct

A note on easy and efficient computation of full abelian periods of a word

2016

Constantinescu and Ilie (Bulletin of the EATCS 89, 167-170, 2006) introduced the idea of an Abelian period with head and tail of a finite word. An Abelian period is called full if both the head and the tail are empty. We present a simple and easy-to-implement $O(n\log\log n)$-time algorithm for computing all the full Abelian periods of a word of length $n$ over a constant-size alphabet. Experiments show that our algorithm significantly outperforms the $O(n)$ algorithm proposed by Kociumaka et al. (Proc. of STACS, 245-256, 2013) for the same problem.

FOS: Computer and information sciencesDiscrete Mathematics (cs.DM)Formal Languages and Automata Theory (cs.FL)[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS][INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS]Elementary abelian groupComputer Science - Formal Languages and Automata Theory0102 computer and information sciences02 engineering and technology[INFO] Computer Science [cs]01 natural sciencesRank of an abelian groupCombinatoricsSimple (abstract algebra)Computer Science - Data Structures and Algorithms0202 electrical engineering electronic engineering information engineeringDiscrete Mathematics and CombinatoricsData Structures and Algorithms (cs.DS)[INFO]Computer Science [cs]Abelian groupHidden subgroup problemDiscrete Mathematics and CombinatoricComputingMilieux_MISCELLANEOUSMathematicsCombinatorics on wordDiscrete mathematicsApplied Mathematics020206 networking & telecommunicationsAbelian periodText algorithmWeak repetitionFree abelian groupAbelian powerCombinatorics on wordsDesign of algorithm010201 computation theory & mathematicsWord (computer architecture)Computer Science::Formal Languages and Automata TheoryComputer Science - Discrete Mathematics
researchProduct

On the Structure of Bispecial Sturmian Words

2013

A balanced word is one in which any two factors of the same length contain the same number of each letter of the alphabet up to one. Finite binary balanced words are called Sturmian words. A Sturmian word is bispecial if it can be extended to the left and to the right with both letters remaining a Sturmian word. There is a deep relation between bispecial Sturmian words and Christoffel words, that are the digital approximations of Euclidean segments in the plane. In 1997, J. Berstel and A. de Luca proved that \emph{palindromic} bispecial Sturmian words are precisely the maximal internal factors of \emph{primitive} Christoffel words. We extend this result by showing that bispecial Sturmian wo…

FOS: Computer and information sciencesGeneral Computer ScienceSpecial factorDiscrete Mathematics (cs.DM)Computer Networks and CommunicationsApproximations of πFormal Languages and Automata Theory (cs.FL)Computer Science - Formal Languages and Automata TheoryEnumerative formula68R15Characterization (mathematics)Minimal forbidden wordTheoretical Computer ScienceCombinatoricsComputer Science::Discrete MathematicsEuclidean geometryPhysics::Atomic PhysicsMathematicsChristoffel symbolsApplied MathematicsPalindromeSturmian wordSturmian wordComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Combinatorics on wordsComputational Theory and MathematicsWord (group theory)Computer Science::Formal Languages and Automata TheoryChristoffel wordComputer Science - Discrete Mathematics
researchProduct

On resampling schemes for particle filters with weakly informative observations

2022

We consider particle filters with weakly informative observations (or `potentials') relative to the latent state dynamics. The particular focus of this work is on particle filters to approximate time-discretisations of continuous-time Feynman--Kac path integral models -- a scenario that naturally arises when addressing filtering and smoothing problems in continuous time -- but our findings are indicative about weakly informative settings beyond this context too. We study the performance of different resampling schemes, such as systematic resampling, SSP (Srinivasan sampling process) and stratified resampling, as the time-discretisation becomes finer and also identify their continuous-time l…

FOS: Computer and information sciencesHidden Markov modelparticle filterStatistics and ProbabilityProbability (math.PR)Markovin ketjutStatistics - ComputationMethodology (stat.ME)resamplingFOS: Mathematicsotantanumeerinen analyysiPrimary 65C35 secondary 65C05 65C60 60J25Statistics Probability and UncertaintyFeynman–Kac modeltilastolliset mallitComputation (stat.CO)path integralMathematics - ProbabilityStatistics - Methodologystokastiset prosessit
researchProduct

Primitive sets of words

2020

Given a (finite or infinite) subset $X$ of the free monoid $A^*$ over a finite alphabet $A$, the rank of $X$ is the minimal cardinality of a set $F$ such that $X \subseteq F^*$. We say that a submonoid $M$ generated by $k$ elements of $A^*$ is {\em $k$-maximal} if there does not exist another submonoid generated by at most $k$ words containing $M$. We call a set $X \subseteq A^*$ {\em primitive} if it is the basis of a $|X|$-maximal submonoid. This definition encompasses the notion of primitive word -- in fact, $\{w\}$ is a primitive set if and only if $w$ is a primitive word. By definition, for any set $X$, there exists a primitive set $Y$ such that $X \subseteq Y^*$. We therefore call $Y$…

FOS: Computer and information sciencesPrimitive setDiscrete Mathematics (cs.DM)General Computer ScienceFormal Languages and Automata Theory (cs.FL)Pseudo-repetitionComputer Science - Formal Languages and Automata Theory0102 computer and information sciences02 engineering and technology01 natural sciencesTheoretical Computer ScienceCombinatoricsCardinalityFree monoidBi-rootFOS: Mathematics0202 electrical engineering electronic engineering information engineeringMathematics - CombinatoricsRank (graph theory)Primitive root modulo nMathematicsHidden repetitionSettore INF/01 - InformaticaIntersection (set theory)k-maximal monoidFunction (mathematics)Basis (universal algebra)010201 computation theory & mathematics020201 artificial intelligence & image processingCombinatorics (math.CO)Computer Science::Formal Languages and Automata TheoryWord (group theory)Computer Science - Discrete Mathematics
researchProduct

Minimal forbidden factors of circular words

2017

Minimal forbidden factors are a useful tool for investigating properties of words and languages. Two factorial languages are distinct if and only if they have different (antifactorial) sets of minimal forbidden factors. There exist algorithms for computing the minimal forbidden factors of a word, as well as of a regular factorial language. Conversely, Crochemore et al. [IPL, 1998] gave an algorithm that, given the trie recognizing a finite antifactorial language $M$, computes a DFA recognizing the language whose set of minimal forbidden factors is $M$. In the same paper, they showed that the obtained DFA is minimal if the input trie recognizes the minimal forbidden factors of a single word.…

FOS: Computer and information sciencesSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniGeneral Computer ScienceDiscrete Mathematics (cs.DM)Finite automatonSettore INF/01 - InformaticaFormal Languages and Automata Theory (cs.FL)Factor automatonComputer Science - Formal Languages and Automata TheoryComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Circular wordFibonacci wordMinimal forbidden factorTheoretical Computer ScienceComputer Science::Formal Languages and Automata TheoryComputer Science - Discrete Mathematics
researchProduct