Search results for " Mach"

showing 10 items of 1388 documents

Deep Non-Line-of-Sight Reconstruction

2020

The recent years have seen a surge of interest in methods for imaging beyond the direct line of sight. The most prominent techniques rely on time-resolved optical impulse responses, obtained by illuminating a diffuse wall with an ultrashort light pulse and observing multi-bounce indirect reflections with an ultrafast time-resolved imager. Reconstruction of geometry from such data, however, is a complex non-linear inverse problem that comes with substantial computational demands. In this paper, we employ convolutional feed-forward networks for solving the reconstruction problem efficiently while maintaining good reconstruction quality. Specifically, we devise a tailored autoencoder architect…

FOS: Computer and information sciencesComputer Science - Machine Learningbusiness.industryComputer scienceComputer Vision and Pattern Recognition (cs.CV)Image and Video Processing (eess.IV)Computer Science - Computer Vision and Pattern RecognitionNonlinear optics020207 software engineering02 engineering and technologyIterative reconstructionInverse problemElectrical Engineering and Systems Science - Image and Video ProcessingAutoencoderRendering (computer graphics)Machine Learning (cs.LG)Non-line-of-sight propagation0202 electrical engineering electronic engineering information engineeringFOS: Electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusiness
researchProduct

Dual Extrapolation for Sparse Generalized Linear Models

2020

International audience; Generalized Linear Models (GLM) form a wide class of regression and classification models, where prediction is a function of a linear combination of the input variables. For statistical inference in high dimension, sparsity inducing regularizations have proven to be useful while offering statistical guarantees. However, solving the resulting optimization problems can be challenging: even for popular iterative algorithms such as coordinate descent, one needs to loop over a large number of variables. To mitigate this, techniques known as screening rules and working sets diminish the size of the optimization problem at hand, either by progressively removing variables, o…

FOS: Computer and information sciencesComputer Science - Machine Learningextrapolation[MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC]Machine Learning (stat.ML)working setsgeneralized linear models[STAT.ML] Statistics [stat]/Machine Learning [stat.ML]Convex optimizationscreening rulesMachine Learning (cs.LG)[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]Statistics - Machine Learning[MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC]Lassosparse logistic regression
researchProduct

Human experts vs. machines in taxa recognition

2020

The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and in the identification logic of taxonomic experts and machines. We propose a systematic approach utilizing deep Convolutional Neural Nets with the transfer learning paradigm and extensively evaluate it over a multi-pose taxonomic dataset with hierarchical labels specifically created for this comparison. We also study the prediction accuracy on different ranks of taxonomic hier…

FOS: Computer and information sciencesComputer Science - Machine Learninghahmontunnistus (tietotekniikka)Computer scienceClassification approachTaxonomic expert02 engineering and technologyneuroverkotcomputer.software_genreConvolutional neural networkQuantitative Biology - Quantitative MethodsField (computer science)Machine Learning (cs.LG)Machine learning approachesStatistics - Machine LearningAutomated approachDeep neural networks0202 electrical engineering electronic engineering information engineeringTaxonomic rankQuantitative Methods (q-bio.QM)Classification (of information)Artificial neural networksystematiikka (biologia)Prediction accuracyIdentification (information)koneoppiminenMulti-image dataBenchmark (computing)020201 artificial intelligence & image processingConvolutional neural networksComputer Vision and Pattern RecognitionClassification errorsMachine Learning (stat.ML)Machine learningState of the artElectrical and Electronic EngineeringTaxonomySupport vector machinesLearning systemsbusiness.industryNode (networking)020206 networking & telecommunicationsComputer circuitsHierarchical classificationConvolutionSupport vector machineFOS: Biological sciencesTaxonomic hierarchySignal ProcessingBiomonitoringBenchmark datasetsArtificial intelligencebusinesscomputertaksonitSoftware
researchProduct

Graphical model inference : Sequential Monte Carlo meets deterministic approximations

2019

Approximate inference in probabilistic graphical models (PGMs) can be grouped into deterministic methods and Monte-Carlo-based methods. The former can often provide accurate and rapid inferences, but are typically associated with biases that are hard to quantify. The latter enjoy asymptotic consistency, but can suffer from high computational costs. In this paper we present a way of bridging the gap between deterministic and stochastic inference. Specifically, we suggest an efficient sequential Monte Carlo (SMC) algorithm for PGMs which can leverage the output from deterministic inference methods. While generally applicable, we show explicitly how this can be done with loopy belief propagati…

FOS: Computer and information sciencesComputer Science - Machine Learningkoneoppiminenmachine learningStatistics - Machine LearningMachine Learning (stat.ML)statistical modelstilastolliset mallitComputer Science::DatabasesMachine Learning (cs.LG)
researchProduct

An Empirical Investigation into Deep and Shallow Rule Learning

2021

Inductive rule learning is arguably among the most traditional paradigms in machine learning. Although we have seen considerable progress over the years in learning rule-based theories, all state-of-the-art learners still learn descriptions that directly relate the input features to the target concept. In the simplest case, concept learning, this is a disjunctive normal form (DNF) description of the positive class. While it is clear that this is sufficient from a logical point of view because every logical expression can be reduced to an equivalent DNF expression, it could nevertheless be the case that more structured representations, which form deep theories by forming intermediate concept…

FOS: Computer and information sciencesComputer Science - Machine Learninglearning in logicComputer Science - Artificial Intelligencedeep learningmini-batch learningQA75.5-76.95stochastic optimizationMachine Learning (cs.LG)inductive rule learningArtificial Intelligence (cs.AI)Artificial IntelligenceElectronic computers. Computer scienceOriginal Research
researchProduct

Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation.

2020

Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and w…

FOS: Computer and information sciencesComputer Science - Machine Learningstochastic local searchrule extractionComputer Science - Artificial Intelligencelogical rulesQA75.5-76.95004 InformatikMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Artificial IntelligenceElectronic computers. Computer scienceconvolutional neural networksk-term DNFinterpretability004 Data processingOriginal ResearchFrontiers in artificial intelligence
researchProduct

Semantics of UML 2.0 Activity Diagram for Business Modeling by Means of Virtual Machine

2005

The paper proposes a more formalized definition of UML 2.0 Activity Diagram semantics. A subset of activity diagram constructs relevant for business process modeling is considered. The semantics definition is based on the original token flow methodology, but a more constructive approach is used. The Activity Diagram Virtual machine is defined by means of a metamodel, with operations defined by a mix of pseudocode and OCL pre- and postconditions. A formal procedure is described which builds the virtual machine for any activity diagram. The relatively complicated original token movement rules in control nodes and edges are combined into paths from an action to action. A new approach is the us…

FOS: Computer and information sciencesComputer Science - Programming LanguagesSemantics (computer science)Computer scienceProgramming languageActivity diagramBusiness process modelingSecurity tokencomputer.software_genreMetamodelingComputational Engineering Finance and Science (cs.CE)Unified Modeling LanguageVirtual machineComputer Science - Computational Engineering Finance and SciencePseudocodecomputercomputer.programming_languageProgramming Languages (cs.PL)
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

Compressed Particle Methods for Expensive Models With Application in Astronomy and Remote Sensing

2021

In many inference problems, the evaluation of complex and costly models is often required. In this context, Bayesian methods have become very popular in several fields over the last years, in order to obtain parameter inversion, model selection or uncertainty quantification. Bayesian inference requires the approximation of complicated integrals involving (often costly) posterior distributions. Generally, this approximation is obtained by means of Monte Carlo (MC) methods. In order to reduce the computational cost of the corresponding technique, surrogate models (also called emulators) are often employed. Another alternative approach is the so-called Approximate Bayesian Computation (ABC) sc…

FOS: Computer and information sciencesComputer scienceAstronomyModel selectionBayesian inferenceMonte Carlo methodBayesian probabilityAerospace EngineeringAstronomyInferenceMachine Learning (stat.ML)Context (language use)Bayesian inferenceStatistics - ComputationComputational Engineering Finance and Science (cs.CE)remote sensingimportance samplingStatistics - Machine Learningnumerical inversionparticle filteringElectrical and Electronic EngineeringUncertainty quantificationApproximate Bayesian computationComputer Science - Computational Engineering Finance and ScienceComputation (stat.CO)IEEE Transactions on Aerospace and Electronic Systems
researchProduct

A survey of active learning algorithms for supervised remote sensing image classification

2011

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active …

FOS: Computer and information sciencesComputer scienceComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionMachine learningcomputer.software_genreactive learningHyperspectral image classificationEntropy (information theory)Electrical and Electronic EngineeringArchitectureRemote sensingvery high resolution (VHR)PixelContextual image classificationbusiness.industryHyperspectral imagingSupport vector machinehyperspectraltraining set definitionSignal Processingsupport vector machine (SVM)Artificial intelligenceHeuristicsbusinessAlgorithmcomputerimage classification
researchProduct