Search results for "Deep Neural Networks"

showing 10 items of 18 documents

Deep neural attention-based model for the evaluation of italian sentences complexity

2020

In this paper, the Automatic Text Complexity Evaluation problem is modeled as a binary classification task tackled by a Neural Network based system. It exploits Recurrent Neural Units and the Attention mechanism to measure the complexity of sentences written in the Italian language. An accurate test phase has been carried out, and the system has been compared with state-of-art tools that tackle the same problem. The computed performances proof the model suitability to evaluate sentence complexity improving the results achieved by other state-of-the-art systems.

050101 languages & linguisticsExploitComputer science02 engineering and technologyText complexity evaluationMachine learningcomputer.software_genreTask (project management)Text Simplification0202 electrical engineering electronic engineering information engineering0501 psychology and cognitive sciencesSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniMeasure (data warehouse)Deep Neural NetworksArtificial neural networkSettore INF/01 - Informaticabusiness.industryItalian languageNatural language processing05 social sciencesComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Deep learningText ComplexityBinary classification020201 artificial intelligence & image processingArtificial intelligenceTest phasebusinesscomputerSentence
researchProduct

Multi-class Text Complexity Evaluation via Deep Neural Networks

2019

Automatic Text Complexity Evaluation (ATE) is a natural language processing task which aims to assess texts difficulty taking into account many facets related to complexity. A large number of papers tackle the problem of ATE by means of machine learning algorithms in order to classify texts into complex or simple classes. In this paper, we try to go beyond the methodologies presented so far by introducing a preliminary system based on a deep neural network model whose objective is to classify sentences into more of two classes. Experiments have been carried out on a manually annotated corpus which has been preprocessed in order to make it suitable for the scope of the paper. The results sho…

050101 languages & linguisticsSettore INF/01 - InformaticaArtificial neural networkText simplificationbusiness.industryComputer science05 social sciencesText simplification02 engineering and technologyDeep neural networkMachine learningcomputer.software_genreClass (biology)Task (project management)Simple (abstract algebra)Automatic Text Complexity Evaluation0202 electrical engineering electronic engineering information engineeringDeep neural networks020201 artificial intelligence & image processing0501 psychology and cognitive sciencesArtificial intelligencebusinesscomputerScope (computer science)
researchProduct

Development of handcrafted and deep based methods for face and facial expression recognition

2021

The research objectives of this thesis concern the development of new concepts for image segmentation and region classification for image analysis. This involves implementing new descriptors, whether color, texture, or shape, to characterize regions and propose new deep learning architectures for the various applications linked to facial analysis. We restrict our focus on face recognition and person-independent facial expressions classification tasks, which are more challenging, especially in unconstrained environments. Our thesis lead to the proposal of many contributions related to facial analysis based on handcrafted and deep architecture.We contributed to face recognition by an effectiv…

Apprentissage profondAnalyse d'images faciales[SPI.OTHER] Engineering Sciences [physics]/OtherMachine learningDeep neural networksDeep learningFacial image analysisRéseaux de neurones profondsApprentissage machineClassificationCnn
researchProduct

Highly Performant, Deep Neural Networks with sub-microsecond latency on FPGAs for Trigger Applications

2020

Artificial neural networks are becoming a standard tool for data analysis, but their potential remains yet to be widely used for hardware-level trigger applications. Nowadays, high-end FPGAs, often used in low-level hardware triggers, offer theoretically enough performance to include networks of considerable size. This makes it very promising and rewarding to optimize a neural network implementation for FPGAs in the trigger context. Here an optimized neural network implementation framework is presented, which typically reaches 90 to 100% computational efficiency, requires few extra FPGA resources for data flow and controlling, and allows latencies in the order of 10s to few 100s of nanoseco…

Artificial neural network010308 nuclear & particles physicsbusiness.industryPhysicsQC1-99901 natural sciencesData flow diagramMicrosecondEmbedded system0103 physical sciencesDeep neural networksLatency (engineering)010306 general physicsField-programmable gate arraybusinessEPJ Web of Conferences
researchProduct

Neural Networks with Multidimensional Cross-Entropy Loss Functions

2019

Deep neural networks have emerged as an effective machine learning tool successfully applied for many tasks, such as misinformation detection, natural language processing, image recognition, machine translation, etc. Neural networks are often applied to binary or multi-class classification problems. In these settings, cross-entropy is used as a loss function for neural network training. In this short note, we propose an extension of the concept of cross-entropy, referred to as multidimensional cross-entropy, and its application as a loss function for classification using neural networks. The presented computational experiments on a benchmark dataset suggest that the proposed approaches may …

Artificial neural networkMachine translationbusiness.industryComputer scienceBinary number02 engineering and technologyFunction (mathematics)Extension (predicate logic)010502 geochemistry & geophysicsMachine learningcomputer.software_genre01 natural sciencesComputingMethodologies_PATTERNRECOGNITIONCross entropy020401 chemical engineeringBenchmark (computing)Deep neural networksArtificial intelligence0204 chemical engineeringbusinesscomputer0105 earth and related environmental sciences
researchProduct

Traitement de données RGB et Lidar à extrêmement haute résolution: retombées de la compétition de fusion de données 2015 de l'IEEE GRSS - Partie A / …

2016

International audience; In this paper, we discuss the scientific outcomes of the 2015 data fusion contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource studies. The 2015 edition of the contest proposed a multiresolution and multisensorial challenge involving extremely high-resolution RGB images and a three-dimensional (3-D) LiDAR point cloud. The competition was framed in two parallel tracks, considering 2-D and 3-D products, respectively. In this paper, we discuss the sci…

Atmospheric Science010504 meteorology & atmospheric sciencesComputer scienceMULTIMODAL-DATA FUSIONGeophysics. Cosmic physics0211 other engineering and technologies02 engineering and technologyCONTESTcomputer.software_genre01 natural sciencesOutcome (game theory)LIDARTraitement des imagesIMAGE ANALYSIS AND DATA FUSION (IADF)DEEP NEURAL NETWORKSDeep neural networksTraitement du signal et de l'imageMULTIRESOLUTION910 Geography & travelMultiresolutionGround truthLANDCOVER CLASSIFICATIONIMAGE AERIENNE1903 Computers in Earth SciencesBenchmarkingVision par ordinateur et reconnaissance de formesOcean engineering10122 Institute of GeographyLidarDeep neural networksData miningExtremely high spatial resolutionMultimodal-data fusionLiDARComputers in Earth Sciences; Atmospheric ScienceImage analysis and data fusion (IADF)EXTREMELY HIGH SPATIAL RESOLUTIONCLASSIFICATIONTRAITEMENT IMAGE1902 Atmospheric ScienceAPPRENTISSAGE STATISTIQUEComputers in Earth SciencesTELEDETECTIONSynthèse d'image et réalité virtuelleTC1501-1800021101 geological & geomatics engineering0105 earth and related environmental sciencesLandcover classificationmultiresolution-[INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB]QC801-809Intelligence artificielleMULTISOURCESensor fusionRGB color modelcomputerMultisource
researchProduct

Deep Neural Networks for Prediction of Exacerbations of Patients with Chronic Obstructive Pulmonary Disease

2018

Chronic Obstructive Pulmonary Disease (COPD) patients need help in daily life situations as they are burdened with frequent risks of acute exacerbation and loss of control. An automated monitoring system could lead to timely treatments and avoid unnecessary hospital (re-)admissions and home visits by doctors or nurses. Therefore we present a Deep Artificial Neural Networks for approach prediction of exacerbations, particularly Feed-Forward Neural Networks (FFNN) for classification of COPD patients category and Long Short-Term Memory (LSTM), for early prediction of COPD exacerbations and subsequent triage. The FFNN and LSTM models are trained on data collected from remote monitoring of 94 pa…

COPDmedicine.medical_specialty020205 medical informaticsExacerbationArtificial neural networkbusiness.industryDeep learningHealth conditionPulmonary disease02 engineering and technologymedicine.diseaseTriage03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineeringMedicineDeep neural networks030212 general & internal medicineArtificial intelligencebusinessIntensive care medicine
researchProduct

A sentence based system for measuring syntax complexity using a recurrent deep neural network

2018

In this paper we present a deep neural network model capable of inducing the rules that identify the syntax complexity of an Italian sentence. Our system, beyond the ability of choosing if a sentence needs of simplification, gives a score that represent the confidence of the model during the process of decision making which could be representative of the sentence complexity. Experiments have been carried out on one public corpus created specifically for the problem of text-simplification.

Deep Neural NetworksComputer Science (all)ComputingMethodologies_DOCUMENTANDTEXTPROCESSINGText simplificationDeep neural networkNatural Language Processing
researchProduct

A recurrent deep neural network model to measure sentence complexity for the Italian Language

2019

Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS…

Deep Neural NetworksText Simplification Natural Language Processing Deep Neural NetworksSettore INF/01 - InformaticaComputingMethodologies_DOCUMENTANDTEXTPROCESSINGAutomatic Text Complexity EvaluationNLP
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