Search results for "learning systems"

showing 7 items of 7 documents

Sequence Learning in a Single Trial: A Spiking Neurons Model Based on Hippocampal Circuitry.

2020

ABSTRACTIn contrast with our everyday experience using brain circuits, it can take a prohibitively long time to train a computational system to produce the correct sequence of outputs in the presence of a series of inputs. This suggests that something important is missing in the way in which models are trying to reproduce basic cognitive functions. In this work, we introduce a new neuronal network architecture that is able to learn, in a single trial, an arbitrary long sequence of any known objects. The key point of the model is the explicit use of mechanisms and circuitry observed in the hippocampus, which allow the model to reach a level of efficiency and accuracy that, to the best of our…

Computer Networks and CommunicationsComputer scienceModels NeurologicalHippocampusAction PotentialsBrain modeling; Computer architecture; Hippocampus; Learning systems; Microprocessors; Navigation; Neurons; Persistent firing (PF); robot navigation; spike-timing-dependent-plasticity synapse; spiking neurons.Hippocampal formationHippocampus03 medical and health sciences0302 clinical medicineArtificial IntelligenceBiological neural network030304 developmental biologyNeurons0303 health sciencesSequenceSeries (mathematics)business.industryBasic cognitive functionsContrast (statistics)CognitionComputer Science ApplicationsSequence learningArtificial intelligenceNeural Networks ComputerbusinessSoftware030217 neurology & neurosurgeryIEEE transactions on neural networks and learning systems
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

Designing the Didactic Strategy Modeling Language (DSML) From PoN: An Activity Oriented EML Proposal

2018

[EN] This paper presents the design of the didactic strategy modeling language (DSML) according to the principles of Physics of Notations (PoN). The DSML is a visual and activity-oriented language for learning design characterized by the representation of different activities according to the nature of the task. Once the language is designed, a blind interpretation study is conducted to validate the semantic transparency of the learning activity iconography. The results of the paper allow to refine the icons. In addition to this, an authoring tool for DSML, which is integrated to an LMS, is presented. As a result, a model driven course was designed as a DSML pre-validation.

Learning systemsModeling languagebusiness.industryGeneral EngineeringModelingTransparency (human–computer interaction)NotationEducationVisualizationTask (project management)Unified Modeling LanguageComputer aided instructionTask analysisSoftware engineeringbusinessRepresentation (mathematics)computerComputer languagesLENGUAJES Y SISTEMAS INFORMATICOScomputer.programming_language
researchProduct

On the analysis of a random walk-jump chain with tree-based transitions and its applications to faulty dichotomous search

2018

Random Walks (RWs) have been extensively studied for more than a century [1]. These walks have traditionally been on a line, and the generalizations for two and three dimensions, have been by extending the random steps to the corresponding neighboring positions in one or many of the dimensions. Among the most popular RWs on a line are the various models for birth and death processes, renewal processes and the gambler’s ruin problem. All of these RWs operate “on a discretized line”, and the walk is achieved by performing small steps to the current-state’s neighbor states. Indeed, it is this neighbor-step motion that renders their analyses tractable. When some of the transitions are to non-ne…

Statistics and ProbabilityCurrent (mathematics)Learning systemsRandom walk jumpsDichotomous searches02 engineering and technologyState (functional analysis)Random walkTime reversibilityBirth–death process020202 computer hardware & architectureChain (algebraic topology)020204 information systemsModeling and SimulationLine (geometry)Controlled random walks0202 electrical engineering electronic engineering information engineeringJumpStatistical physicsTime reversibilitiesMathematics
researchProduct

AI-enabled adaptive learning systems: A systematic mapping of the literature

2021

Abstract Mobile internet, cloud computing, big data technologies, and significant breakthroughs in Artificial Intelligence (AI) have all transformed education. In recent years, there has been an emergence of more advanced AI-enabled learning systems, which are gaining traction due to their ability to deliver learning content and adapt to the individual needs of students. Yet, even though these contemporary learning systems are useful educational platforms that meet students’ needs, there is still a low number of implemented systems designed to address the concerns and problems faced by many students. Based on this perspective, a systematic mapping of the literature on AI-enabled adaptive le…

business.industryComputer sciencePerspective (graphical)Big dataPsychological interventionCloud computingQA75.5-76.95Data scienceComputer Science ApplicationsEducationVisualizationIdentification (information)Artificial IntelligenceAIElectronic computers. Computer scienceAI-Enabled learning systemsAdaptive learningSystematic mappingbusinessAdaptive learning systemsVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550
researchProduct

Practices and Infrastructures for Machine Learning Systems : An Interview Study in Finnish Organizations

2022

Using interviews, we investigated the practices and toolchains for machine learning (ML)-enabled systems from 16 organizations across various domains in Finland. We observed some well-established artificial intelligence engineering approaches, but practices and tools are still needed for the testing and monitoring of ML-enabled systems. Peer reviewed

organizationscomputational modelingliiketoimintaprosessitGeneral Computer Scienceinterviewsbusiness practicesohjelmistotuotantoorganisaatiotmonitorointitekoäly113 Computer and information sciencesartificial intelligencelearning systemsdata modelsmonitoringmachine learningkoneoppiminenälytekniikkahaastattelututkimussoftware engineering
researchProduct

An intelligent learning support system

2017

Fast-growing technologies are shaping many aspects of societies. Educational systems, in general, are still rather traditional: learner applies for school or university, chooses the subject, takes the courses, and finally graduates. The problem is that labor markets are constantly changing and the needed professional skills might not match with the curriculum of the educational program. It might be that it is not even possible to learn a combination of desired skills within one educational organization. For example, there are only a few universities that can provide high-quality teaching in several different areas. Therefore, learners may have to study specific modules and units somewhere e…

ta113intelligent learning systemsoppimisympäristöError-driven learningoppiminenComputer scienceIntelligent decision support system02 engineering and technologyopetuscareer developmenturakehityspersonalized educationHuman–computer interactionadaptive education020204 information systems0202 electrical engineering electronic engineering information engineeringComputingMilieux_COMPUTERSANDEDUCATIONälytekniikka020201 artificial intelligence & image processingLearning supportta516personointi
researchProduct