Search results for " Machine Learning"

showing 10 items of 300 documents

Efficient Nonlinear RX Anomaly Detectors

2020

Current anomaly detection algorithms are typically challenged by either accuracy or efficiency. More accurate nonlinear detectors are typically slow and not scalable. In this letter, we propose two families of techniques to improve the efficiency of the standard kernel Reed-Xiaoli (RX) method for anomaly detection by approximating the kernel function with either {\em data-independent} random Fourier features or {\em data-dependent} basis with the Nystr\"om approach. We compare all methods for both real multi- and hyperspectral images. We show that the proposed efficient methods have a lower computational cost and they perform similar (or outperform) the standard kernel RX algorithm thanks t…

FOS: Computer and information sciencesComputer Science - Machine LearningBasis (linear algebra)Computer scienceComputer Vision and Pattern Recognition (cs.CV)Image and Video Processing (eess.IV)Computer Science - Computer Vision and Pattern Recognition0211 other engineering and technologiesApproximation algorithmHyperspectral imaging02 engineering and technologyElectrical Engineering and Systems Science - Image and Video ProcessingGeotechnical Engineering and Engineering GeologyRegularization (mathematics)Machine Learning (cs.LG)Nonlinear systemKernel (linear algebra)Kernel (statistics)FOS: Electrical engineering electronic engineering information engineeringAnomaly detectionElectrical and Electronic EngineeringAnomaly (physics)Algorithm021101 geological & geomatics engineeringIEEE Geoscience and Remote Sensing Letters
researchProduct

A General Framework for Complex Network-Based Image Segmentation

2019

International audience; With the recent advances in complex networks theory, graph-based techniques for image segmentation has attracted great attention recently. In order to segment the image into meaningful connected components, this paper proposes an image segmentation general framework using complex networks based community detection algorithms. If we consider regions as communities, using community detection algorithms directly can lead to an over-segmented image. To address this problem, we start by splitting the image into small regions using an initial segmentation. The obtained regions are used for building the complex network. To produce meaningful connected components and detect …

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Networks and CommunicationsComputer scienceComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONMachine Learning (stat.ML)02 engineering and technologyMachine Learning (cs.LG)Statistics - Machine Learning0202 electrical engineering electronic engineering information engineeringMedia TechnologySegmentationConnected componentbusiness.industrySimilarity matrix[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020207 software engineeringPattern recognitionImage segmentationComplex networkHardware and ArchitectureComputer Science::Computer Vision and Pattern RecognitionGraph (abstract data type)020201 artificial intelligence & image processingArtificial intelligencebusinessSoftware
researchProduct

Deep Q-Learning With Q-Matrix Transfer Learning for Novel Fire Evacuation Environment

2021

We focus on the important problem of emergency evacuation, which clearly could benefit from reinforcement learning that has been largely unaddressed. Emergency evacuation is a complex task which is difficult to solve with reinforcement learning, since an emergency situation is highly dynamic, with a lot of changing variables and complex constraints that makes it difficult to train on. In this paper, we propose the first fire evacuation environment to train reinforcement learning agents for evacuation planning. The environment is modelled as a graph capturing the building structure. It consists of realistic features like fire spread, uncertainty and bottlenecks. We have implemented the envir…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Artificial IntelligenceComputer scienceQ-learningComputingMilieux_LEGALASPECTSOFCOMPUTINGSystems and Control (eess.SY)02 engineering and technologyOverfittingMachine Learning (cs.LG)FOS: Electrical engineering electronic engineering information engineering0202 electrical engineering electronic engineering information engineeringReinforcement learningElectrical and Electronic EngineeringVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550business.industry020206 networking & telecommunicationsComputer Science ApplicationsHuman-Computer InteractionArtificial Intelligence (cs.AI)Control and Systems EngineeringShortest path problemEmergency evacuationComputer Science - Systems and Control020201 artificial intelligence & image processingArtificial intelligenceTransfer of learningbusinessSoftwareIEEE Transactions on Systems, Man, and Cybernetics: Systems
researchProduct

Approaching sales forecasting using recurrent neural networks and transformers

2022

Accurate and fast demand forecast is one of the hot topics in supply chain for enabling the precise execution of the corresponding downstream processes (inbound and outbound planning, inventory placement, network planning, etc). We develop three alternatives to tackle the problem of forecasting the customer sales at day/store/item level using deep learning techniques and the Corporaci\'on Favorita data set, published as part of a Kaggle competition. Our empirical results show how good performance can be achieved by using a simple sequence to sequence architecture with minimal data preprocessing effort. Additionally, we describe a training trick for making the model more time independent and…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Artificial IntelligenceGeneral Engineeringdeep learningUNESCO::CIENCIAS TECNOLÓGICASStatistics - ApplicationsComputer Science ApplicationsMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Artificial Intelligencesequence to sequencetransformerApplications (stat.AP)sales forecastsupply chain
researchProduct

Structured query construction via knowledge graph embedding

2020

In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Computation and LanguageComputer Science - Artificial Intelligenceknowledge graph embeddingnatural language question answeringkyselykieletMachine Learning (cs.LG)luonnollinen kieliArtificial Intelligence (cs.AI)knowledge graphquery constructionComputation and Language (cs.CL)tietomallit
researchProduct

One-Pixel Attack Deceives Computer-Assisted Diagnosis of Cancer

2020

Computer vision and machine learning can be used to automate various tasks in cancer diagnostic and detection. If an attacker can manipulate the automated processing, the results can be devastating and in the worst case lead to wrong diagnosis and treatment. In this research, the goal is to demonstrate the use of one-pixel attacks in a real-life scenario with a real pathology dataset, TUPAC16, which consists of digitized whole-slide images. We attack against the IBM CODAIT's MAX breast cancer detector using adversarial images. These adversarial examples are found using differential evolution to perform the one-pixel modification to the images in the dataset. The results indicate that a mino…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Cryptography and SecurityComputer scienceComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONMachine Learning (cs.LG)Medical imagingComputer visionkonenäköIBMkyberturvallisuusPixelbusiness.industryPerspective (graphical)diagnostiikkakoneoppiminenDifferential evolutionWhole slide imageReversingsyöpätauditArtificial intelligencebusinessCryptography and Security (cs.CR)verkkohyökkäykset
researchProduct

Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning

2020

Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection of private data. Hence, methods for training neural networks on the joint data of different data owners, that keep each party's input confidential, are called for. We address a specific setting in federated learning, namely that of deep learning from horizontally distributed data with a limited number of parties, where their vulnerable intermediate results have to be processed in a privacy-preserving manner. This setting can be found in medical and healthcare as well as industrial applications. The predominant scheme for this is based on homomorphic encryption…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Cryptography and SecurityStatistics - Machine LearningMachine Learning (stat.ML)Cryptography and Security (cs.CR)Machine Learning (cs.LG)
researchProduct

A Relational Tsetlin Machine with Applications to Natural Language Understanding

2021

TMs are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns. In addition to being natively interpretable, they have provided competitive accuracy for various tasks. In this paper, we increase the computing power of TMs by proposing a first-order logic-based framework with Herbrand semantics. The resulting TM is relational and can take advantage of logical structures appearing in natural language, to learn rules that represent how actions and consequences are related in the real world. The outcome is a logic program of Horn clauses, bringing in a structured view of unstructured data. In closed-domain question-answering, th…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Logic in Computer ScienceComputer Science - Computation and LanguageI.2.4Computer Science - Artificial IntelligenceComputer Networks and CommunicationsI.2.7Machine Learning (cs.LG)Logic in Computer Science (cs.LO)Artificial Intelligence (cs.AI)Artificial IntelligenceHardware and ArchitectureComputation and Language (cs.CL)I.2.7; I.2.4SoftwareInformation Systems
researchProduct

On the Convergence of Tsetlin Machines for the XOR Operator.

2022

The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks. Although numerous papers explore the TM empirically, many of its properties have not yet been analyzed mathematically. In this article, we analyze the convergence of the TM when input is non-linearly related to output by the XOR-operator. Our analysis reveals that the TM, with just two conjunctive clauses, can converge almost surely to reproducing XOR, learning from training data over an infinite time horizon. Furthermore, the analysis shows how the hyper-parameter T guides clause construction so that the clauses c…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Logic in Computer ScienceVDP::Teknologi: 500Artificial Intelligence (cs.AI)Computational Theory and MathematicsArtificial IntelligenceComputer Science - Artificial IntelligenceApplied MathematicsComputer Vision and Pattern RecognitionSoftwareMachine Learning (cs.LG)Logic in Computer Science (cs.LO)IEEE transactions on pattern analysis and machine intelligence
researchProduct

Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams

2023

We investigate the use of Convolutional Neural Networks (including the modern ConvNeXt network family) to classify transient noise signals (i.e.~glitches) and gravitational waves in data from the Advanced LIGO detectors. First, we use models with a supervised learning approach, both trained from scratch using the Gravity Spy dataset and employing transfer learning by fine-tuning pre-trained models in this dataset. Second, we also explore a self-supervised approach, pre-training models with automatically generated pseudo-labels. Our findings are very close to existing results for the same dataset, reaching values for the F1 score of 97.18% (94.15%) for the best supervised (self-supervised) m…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionFOS: Physical sciencesGeneral Relativity and Quantum Cosmology (gr-qc)Astrophysics - Instrumentation and Methods for AstrophysicsInstrumentation and Methods for Astrophysics (astro-ph.IM)General Relativity and Quantum CosmologyMachine Learning (cs.LG)
researchProduct