Bibliographies thématiques / Machine Learning Informé

Sommaire

Articles de revues
Thèses
Livres
Chapitres de livres
Actes de conférences
Rapports d'organisations

Littérature scientifique sur le sujet « Machine Learning Informé »

Auteur : Grafiati

Publié le 21 décembre 2024

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres

Choisissez une source :

Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Machine Learning Informé ».

À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.

Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.

Articles de revues sur le sujet "Machine Learning Informé"

Shoureshi, R., D. Swedes et R. Evans. « Learning Control for Autonomous Machines ». Robotica 9, n^o 2 (avril 1991) : 165–70. http://dx.doi.org/10.1017/s0263574700010201.

Texte intégral

Résumé :

SUMMARYToday's industrial machines and manipulators have no capability to learn by experience. Performance and productivity could be greatly enhanced if a machine could modify its operation based on previous actions. This paper presents a learning control scheme that provides the ability for machines to utilize their past experiences. The objective is to have machines mimic the human learning process as closely as possible. A data base is formulated to provide the machine with experience. An optical infrared distance sensor is developed to inform the machine about objects in its working space. A learning control scheme is presented that utilizes the sensory information to enhance machine performance in the next trial. An adaptive scheme is proposed for the modification of learning gain matrices, and is implemented on an industrial robot. Experimental results verify the potentials of the proposed adaptive learning scheme, and illustrate how it can be used for improvement of different manufacturing processes.

Styles APA, Harvard, Vancouver, ISO, etc.

Pateras, Joseph, Pratip Rana et Preetam Ghosh. « A Taxonomic Survey of Physics-Informed Machine Learning ». Applied Sciences 13, n^o 12 (7 juin 2023) : 6892. http://dx.doi.org/10.3390/app13126892.

Texte intégral

Résumé :

Physics-informed machine learning (PIML) refers to the emerging area of extracting physically relevant solutions to complex multiscale modeling problems lacking sufficient quantity and veracity of data with learning models informed by physically relevant prior information. This work discusses the recent critical advancements in the PIML domain. Novel methods and applications of domain decomposition in physics-informed neural networks (PINNs) in particular are highlighted. Additionally, we explore recent works toward utilizing neural operator learning to intuit relationships in physics systems traditionally modeled by sets of complex governing equations and solved with expensive differentiation techniques. Finally, expansive applications of traditional physics-informed machine learning and potential limitations are discussed. In addition to summarizing recent work, we propose a novel taxonomic structure to catalog physics-informed machine learning based on how the physics-information is derived and injected into the machine learning process. The taxonomy assumes the explicit objectives of facilitating interdisciplinary collaboration in methodology, thereby promoting a wider characterization of what types of physics problems are served by the physics-informed learning machines and assisting in identifying suitable targets for future work. To summarize, the major twofold goal of this work is to summarize recent advancements and introduce a taxonomic catalog for applications of physics-informed machine learning.

Styles APA, Harvard, Vancouver, ISO, etc.

Minasny, Budiman, Toshiyuki Bandai, Teamrat A. Ghezzehei, Yin-Chung Huang, Yuxin Ma, Alex B. McBratney, Wartini Ng et al. « Soil Science-Informed Machine Learning ». Geoderma 452 (décembre 2024) : 117094. http://dx.doi.org/10.1016/j.geoderma.2024.117094.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Xypakis, Emmanouil, Valeria deTurris, Fabrizio Gala, Giancarlo Ruocco et Marco Leonetti. « Physics-informed machine learning for microscopy ». EPJ Web of Conferences 266 (2022) : 04007. http://dx.doi.org/10.1051/epjconf/202226604007.

Texte intégral

Résumé :

We developed a physics-informed deep neural network architecture able to achieve signal to noise ratio improvements starting from low exposure noisy data. Our model is based on the nature of the photon detection process characterized by a Poisson probability distribution which we included in the training loss function. Our approach surpasses previous algorithms performance for microscopy data, moreover, the generality of the physical concepts employed here, makes it readily exportable to any imaging context.

Styles APA, Harvard, Vancouver, ISO, etc.

Zhao, Hefei, Yinglun Zhan, Joshua Nduwamungu, Yuzhen Zhou, Changmou Xu et Zheng Xu. « Machine learning-driven Raman spectroscopy for rapidly detecting type, adulteration, and oxidation of edible oils ». INFORM International News on Fats, Oils, and Related Materials 31, n^o 4 (1 avril 2020) : 12–15. http://dx.doi.org/10.21748/inform.04.2020.12.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Serre, Thomas. « Deep Learning : The Good, the Bad, and the Ugly ». Annual Review of Vision Science 5, n^o 1 (15 septembre 2019) : 399–426. http://dx.doi.org/10.1146/annurev-vision-091718-014951.

Texte intégral

Résumé :

Artificial vision has often been described as one of the key remaining challenges to be solved before machines can act intelligently. Recent developments in a branch of machine learning known as deep learning have catalyzed impressive gains in machine vision—giving a sense that the problem of vision is getting closer to being solved. The goal of this review is to provide a comprehensive overview of recent deep learning developments and to critically assess actual progress toward achieving human-level visual intelligence. I discuss the implications of the successes and limitations of modern machine vision algorithms for biological vision and the prospect for neuroscience to inform the design of future artificial vision systems.

Styles APA, Harvard, Vancouver, ISO, etc.

Arundel, Samantha T., Gaurav Sinha, Wenwen Li, David P. Martin, Kevin G. McKeehan et Philip T. Thiem. « Historical maps inform landform cognition in machine learning ». Abstracts of the ICA 6 (11 août 2023) : 1–2. http://dx.doi.org/10.5194/ica-abs-6-10-2023.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Karimpouli, Sadegh, et Pejman Tahmasebi. « Physics informed machine learning : Seismic wave equation ». Geoscience Frontiers 11, n^o 6 (novembre 2020) : 1993–2001. http://dx.doi.org/10.1016/j.gsf.2020.07.007.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Zhang, Xi. « Application of Machine Learning in Stock Price Analysis ». Highlights in Science, Engineering and Technology 107 (15 août 2024) : 143–49. http://dx.doi.org/10.54097/tjhsx998.

Texte intégral

Résumé :

With the advancement of technology, machine learning has emerged as a powerful tool for analyzing complex financial data, including stock prices. By leveraging algorithms capable of identifying patterns and trends, it offers insights into market behavior. This study explores the application of machine learning techniques in stock price analysis, aiming to enhance prediction accuracy and inform investment decisions. Through rigorous analysis, our research demonstrates that machine learning models can effectively capture the dynamic nature of stock markets, leading to improved forecasting capabilities. The results indicate a significant enhancement in prediction accuracy, suggesting that these techniques could significantly contribute to financial analysis. The significance of this study lies in its potential to revolutionize stock market analysis. By harnessing the predictive power of machine learning, investors can make more informed decisions, reduce risks, and enhance returns. This not only benefits individual investors but also contributes to the overall stability and efficiency of financial markets. Machine Learning, Stock Price Analysis, Prediction Accuracy, Financial Markets, Investment Decision-Making. The methods employed in this study include the utilization of various machine learning algorithms such as support vector machines and neural networks, as well as the application of statistical techniques for data analysis and validation.

Styles APA, Harvard, Vancouver, ISO, etc.

Liu, Yang, Ruo Jia, Jieping Ye et Xiaobo Qu. « How machine learning informs ride-hailing services : A survey ». Communications in Transportation Research 2 (décembre 2022) : 100075. http://dx.doi.org/10.1016/j.commtr.2022.100075.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Plus de sources

Thèses sur le sujet "Machine Learning Informé"

Guimbaud, Jean-Baptiste. « Enhancing Environmental Risk Scores with Informed Machine Learning and Explainable AI ». Electronic Thesis or Diss., Lyon 1, 2024. http://www.theses.fr/2024LYO10188.

Texte intégral

Résumé :

Dès la conception, des facteurs environnementaux tels que la qualité de l'air ou les habitudes alimentaires peuvent significativement influencer le risque de développer diverses maladies chroniques. Dans la littérature épidémiologique, des indicateurs connus sous le nom de Scores de Risque Environnemental (Environmental Risk Score, ERS) sont utilisés non seulement pour identifier les individus à risque, mais aussi pour étudier les relations entre les facteurs environnementaux et la santé. Une limite de la plupart des ERSs est qu'ils sont exprimés sous forme de combinaisons linéaires d'un nombre limité de facteurs. Cette thèse de doctorat vise à développer des indicateurs ERSs capables d'investiguer des relations non linéaires et des interactions à travers un large éventail d'expositions tout en découvrant des facteurs actionnables pour guider des mesures et interventions préventives, tant chez les adultes que chez les enfants. Pour atteindre cet objectif, nous exploitons les capacités prédictives des méthodes d'apprentissage automatique non paramétriques, combinées avec des outils récents d'IA explicable et des connaissances existantes du domaine. Dans la première partie de cette thèse, nous calculons des scores de risque environnemental basés sur l'apprentissage automatique pour la santé mentale, cardiométabolique et respiratoire de l'enfant. En plus d'identifier des relations non linéaires et des interactions entre expositions, nous avons identifié de nouveaux prédicteurs de maladies chez les enfants. Les scores peuvent expliquer une proportion significative de la variance des données et leurs performances sont stables à travers différentes cohortes. Dans la deuxième partie, nous proposons SEANN, une nouvelle approche intégrant des connaissances expertes sous forme d'Effet Agrégées (Pooled Effect Size, PES) dans l'entraînement de réseaux neuronaux profonds pour le calcul de scores de risque environnemental informés (Informed ERS). SEANN vise à calculer des ERSs plus robustes, généralisables à une population plus large, et capables de capturer des relations d'exposition plus proches de celles connues dans la littérature. Nous illustrons expérimentalement les avantages de cette approche en utilisant des données synthétiques. Par rapport à un réseau neuronal agnostique, nous obtenons une meilleure généralisation des prédictions dans des contextes de données bruitées et une fiabilité améliorée des interprétations obtenues en utilisant des méthodes d'Intelligence Artificielle Explicable (Explainable AI - XAI).Dans la dernière partie de cette thèse, nous proposons une application concrète de SEANN en utilisant les données d'une cohorte espagnole composée d'adultes. Comparé à un score de risque environnemental basé sur un réseau neuronal agnostique, le score obtenu avec SEANN capture des relations mieux alignées avec les associations de la littérature sans détériorer les performances prédictives. De plus, les expositions ayant une couverture littéraire limitée diffèrent significativement de celles obtenues avec la méthode agnostique de référence en bénéficiant de directions d'associations plus plausibles. En conclusion, nos scores de risque démontrent un indubitable potentiel pour la découverte informée de relation environnement-santé non linéaires peu connues, tirant parti des connaissances existantes sur les relations bien connues. Au-delà de leur utilité dans la recherche épidémiologique, nos indicateurs de risque sont capables de capturer, de manière holistique, des relations de risque au niveau individuel et d'informer les praticiens sur des facteurs de risque actionnables identifiés. Alors que dans l'ère post-génétique, la prévention en médecine personnalisée se concentrera de plus en plus sur les facteurs non héréditaires et actionnables, nous pensons que ces approches seront déterminantes pour façonner les futurs paradigmes de la santé
From conception onward, environmental factors such as air quality or dietary habits can significantly impact the risk of developing various chronic diseases. Within the epidemiological literature, indicators known as Environmental Risk Scores (ERSs) are used not only to identify individuals at risk but also to study the relationships between environmental factors and health. A limit of most ERSs is that they are expressed as linear combinations of a limited number of factors. This doctoral thesis aims to develop ERS indicators able to investigate nonlinear relationships and interactions across a broad range of exposures while discovering actionable factors to guide preventive measures and interventions, both in adults and children. To achieve this aim, we leverage the predictive abilities of non-parametric machine learning methods, combined with recent Explainable AI tools and existing domain knowledge. In the first part of this thesis, we compute machine learning-based environmental risk scores for mental, cardiometabolic, and respiratory general health for children. On top of identifying nonlinear relationships and exposure-exposure interactions, we identified new predictors of disease in childhood. The scores could explain a significant proportion of variance and their performances were stable across different cohorts. In the second part, we propose SEANN, a new approach integrating expert knowledge in the form of Pooled Effect Sizes (PESs) into the training of deep neural networks for the computation of extit{informed environmental risk scores}. SEANN aims to compute more robust ERSs, generalizable to a broader population, and able to capture exposure relationships that are closer to evidence known from the literature. We experimentally illustrate the approach's benefits using synthetic data, showing improved prediction generalizability in noisy contexts (i.e., observational settings) and improved reliability of interpretation using Explainable Artificial Intelligence (XAI) methods compared to an agnostic neural network. In the last part of this thesis, we propose a concrete application for SEANN using data from a cohort of Spanish adults. Compared to an agnostic neural network-based ERS, the score obtained with SEANN effectively captures relationships more in line with the literature-based associations without deteriorating the predictive performances. Moreover, exposures with poor literature coverage significantly differ from those obtained with the agnostic baseline method with more plausible directions of associations.In conclusion, our risk scores demonstrate substantial potential for the data-driven discovery of unknown nonlinear environmental health relationships by leveraging existing knowledge about well-known relationships. Beyond their utility in epidemiological research, our risk indicators are able to capture holistic individual-level non-hereditary risk associations that can inform practitioners about actionable factors in high-risk individuals. As in the post-genetic era, personalized medicine prevention will focus more and more on modifiable factors, we believe that such approaches will be instrumental in shaping future healthcare paradigms

Styles APA, Harvard, Vancouver, ISO, etc.

Mack, Jonas. « Physics Informed Machine Learning of Nonlinear Partial Differential Equations ». Thesis, Uppsala universitet, Tillämpad matematik och statistik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-441275.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Leung, Jason W. « Application of machine learning : automated trading informed by event driven data ». Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/105982.

Texte intégral

Résumé :

Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 61-65).
Models of stock price prediction have traditionally used technical indicators alone to generate trading signals. In this paper, we build trading strategies by applying machine-learning techniques to both technical analysis indicators and market sentiment data. The resulting prediction models can be employed as an artificial trader used to trade on any given stock exchange. The performance of the model is evaluated using the S&P 500 index.
by Jason W. Leung.
M. Eng.

Styles APA, Harvard, Vancouver, ISO, etc.

Wu, Jinlong. « Predictive Turbulence Modeling with Bayesian Inference and Physics-Informed Machine Learning ». Diss., Virginia Tech, 2018. http://hdl.handle.net/10919/85129.

Texte intégral

Résumé :

Reynolds-Averaged Navier-Stokes (RANS) simulations are widely used for engineering design and analysis involving turbulent flows. In RANS simulations, the Reynolds stress needs closure models and the existing models have large model-form uncertainties. Therefore, the RANS simulations are known to be unreliable in many flows of engineering relevance, including flows with three-dimensional structures, swirl, pressure gradients, or curvature. This lack of accuracy in complex flows has diminished the utility of RANS simulations as a predictive tool for engineering design, analysis, optimization, and reliability assessments. Recently, data-driven methods have emerged as a promising alternative to develop the model of Reynolds stress for RANS simulations. In this dissertation I explore two physics-informed, data-driven frameworks to improve RANS modeled Reynolds stresses. First, a Bayesian inference framework is proposed to quantify and reduce the model-form uncertainty of RANS modeled Reynolds stress by leveraging online sparse measurement data with empirical prior knowledge. Second, a machine-learning-assisted framework is proposed to utilize offline high-fidelity simulation databases. Numerical results show that the data-driven RANS models have better prediction of Reynolds stress and other quantities of interest for several canonical flows. Two metrics are also presented for an a priori assessment of the prediction confidence for the machine-learning-assisted RANS model. The proposed data-driven methods are also applicable to the computational study of other physical systems whose governing equations have some unresolved physics to be modeled.
Ph. D.
Reynolds-Averaged Navier–Stokes (RANS) simulations are widely used for engineering design and analysis involving turbulent flows. In RANS simulations, the Reynolds stress needs closure models and the existing models have large model-form uncertainties. Therefore, the RANS simulations are known to be unreliable in many flows of engineering relevance, including flows with three-dimensional structures, swirl, pressure gradients, or curvature. This lack of accuracy in complex flows has diminished the utility of RANS simulations as a predictive tool for engineering design, analysis, optimization, and reliability assessments. Recently, data-driven methods have emerged as a promising alternative to develop the model of Reynolds stress for RANS simulations. In this dissertation I explore two physics-informed, data-driven frameworks to improve RANS modeled Reynolds stresses. First, a Bayesian inference framework is proposed to quantify and reduce the model-form uncertainty of RANS modeled Reynolds stress by leveraging online sparse measurement data with empirical prior knowledge. Second, a machine-learning-assisted framework is proposed to utilize offline high fidelity simulation databases. Numerical results show that the data-driven RANS models have better prediction of Reynolds stress and other quantities of interest for several canonical flows. Two metrics are also presented for an a priori assessment of the prediction confidence for the machine-learning-assisted RANS model. The proposed data-driven methods are also applicable to the computational study of other physical systems whose governing equations have some unresolved physics to be modeled.

Styles APA, Harvard, Vancouver, ISO, etc.

Reichert, Nils. « CORRELATION BETWEEN COMPUTER RECOGNIZED FACIAL EMOTIONS AND INFORMED EMOTIONS DURING A CASINO COMPUTER GAME ». Thesis, Fredericton : University of New Brunswick, 2012. http://hdl.handle.net/1882/44596.

Texte intégral

Résumé :

Emotions play an important role for everyday communication. Different methods allow computers to recognize emotions. Most are trained with acted emotions and it is unknown if such a model would work for recognizing naturally appearing emotions. An experiment was setup to estimate the recognition accuracy of the emotion recognition software SHORE, which could detect the emotions angry, happy, sad, and surprised. Subjects played a casino game while being recorded. The software recognition was correlated with the recognition of ten human observers. The results showed a strong recognition for happy, medium recognition for surprised, and a weak recognition for sad and angry faces. In addition, questionnaires containing self-informed emotions were compared with the computer recognition, but only weak correlations were found. SHORE was able to recognize emotions almost as well as humans were, but if humans had problems to recognize an emotion, then the accuracy of the software was much lower.

Styles APA, Harvard, Vancouver, ISO, etc.

Wang, Jianxun. « Physics-Informed, Data-Driven Framework for Model-Form Uncertainty Estimation and Reduction in RANS Simulations ». Diss., Virginia Tech, 2017. http://hdl.handle.net/10919/77035.

Texte intégral

Résumé :

Computational fluid dynamics (CFD) has been widely used to simulate turbulent flows. Although an increased availability of computational resources has enabled high-fidelity simulations (e.g. large eddy simulation and direct numerical simulation) of turbulent flows, the Reynolds-Averaged Navier-Stokes (RANS) equations based models are still the dominant tools for industrial applications. However, the predictive capability of RANS models is limited by potential inaccuracies driven by hypotheses in the Reynolds stress closure. With the ever-increasing use of RANS simulations in mission-critical applications, the estimation and reduction of model-form uncertainties in RANS models have attracted attention in the turbulence modeling community. In this work, I focus on estimating uncertainties stemming from the RANS turbulence closure and calibrating discrepancies in the modeled Reynolds stresses to improve the predictive capability of RANS models. Both on-line and off-line data are utilized to achieve this goal. The main contributions of this dissertation can be summarized as follows: First, a physics-based, data-driven Bayesian framework is developed for estimating and reducing model-form uncertainties in RANS simulations. An iterative ensemble Kalman method is employed to assimilate sparse on-line measurement data and empirical prior knowledge for a full-field inversion. The merits of incorporating prior knowledge and physical constraints in calibrating RANS model discrepancies are demonstrated and discussed. Second, a random matrix theoretic framework is proposed for estimating model-form uncertainties in RANS simulations. Maximum entropy principle is employed to identify the probability distribution that satisfies given constraints but without introducing artificial information. Objective prior perturbations of RANS-predicted Reynolds stresses in physical projections are provided based on comparisons between physics-based and random matrix theoretic approaches. Finally, a physics-informed, machine learning framework towards predictive RANS turbulence modeling is proposed. The functional forms of model discrepancies with respect to mean flow features are extracted from the off-line database of closely related flows based on machine learning algorithms. The RANS-modeled Reynolds stresses of prediction flows can be significantly improved by the trained discrepancy function, which is an important step towards the predictive turbulence modeling.
Ph. D.

Styles APA, Harvard, Vancouver, ISO, etc.

Cedergren, Linnéa. « Physics-informed Neural Networks for Biopharma Applications ». Thesis, Umeå universitet, Institutionen för fysik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-185423.

Texte intégral

Résumé :

Physics-Informed Neural Networks (PINNs) are hybrid models that incorporate differential equations into the training of neural networks, with the aim of bringing the best of both worlds. This project used a mathematical model describing a Continuous Stirred-Tank Reactor (CSTR), to test two possible applications of PINNs. The first type of PINN was trained to predict an unknown reaction rate law, based only on the differential equation and a time series of the reactor state. The resulting model was used inside a multi-step solver to simulate the system state over time. The results showed that the PINN could accurately model the behaviour of the missing physics also for new initial conditions. However, the model suffered from extrapolation error when tested on a larger reactor, with a much lower reaction rate. Comparisons between using a numerical derivative or automatic differentiation in the loss equation, indicated that the latter had a higher robustness to noise. Thus, it is likely the best choice for real applications. A second type of PINN was trained to forecast the system state one-step-ahead based on previous states and other known model parameters. An ordinary feed-forward neural network with an equal architecture was used as baseline. The second type of PINN did not outperform the baseline network. Further studies are needed to conclude if or when physics-informed loss should be used in autoregressive applications.

Styles APA, Harvard, Vancouver, ISO, etc.

Emerson, Guy Edward Toh. « Functional distributional semantics : learning linguistically informed representations from a precisely annotated corpus ». Thesis, University of Cambridge, 2018. https://www.repository.cam.ac.uk/handle/1810/284882.

Texte intégral

Résumé :

The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors - but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about 'truth', a crucial concept in logic and formal semantics. In this thesis, I develop a framework for distributional semantics which answers this challenge. The meaning of a word is not represented as a vector, but as a 'function', mapping entities (objects in the world) to probabilities of truth (the probability that the word is true of the entity). Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models.

Styles APA, Harvard, Vancouver, ISO, etc.

Giuliani, Luca. « Extending the Moving Targets Method for Injecting Constraints in Machine Learning ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23885/.

Texte intégral

Résumé :

Informed Machine Learning is an umbrella term that comprises a set of methodologies in which domain knowledge is injected into a data-driven system in order to improve its level of accuracy, satisfy some external constraint, and in general serve the purposes of explainability and reliability. The said topid has been widely explored in the literature by means of many different techniques. Moving Targets is one such a technique particularly focused on constraint satisfaction: it is based on decomposition and bi-level optimization and proceeds by iteratively refining the target labels through a master step which is in charge of enforcing the constraints, while the training phase is delegated to a learner. In this work, we extend the algorithm in order to deal with semi-supervised learning and soft constraints. In particular, we focus our empirical evaluation on both regression and classification tasks involving monotonicity shape constraints. We demonstrate that our method is robust with respect to its hyperparameters, as well as being able to generalize very well while reducing the number of violations on the enforced constraints. Additionally, the method can even outperform, both in terms of accuracy and constraint satisfaction, other state-of-the-art techniques such as Lattice Models and Semantic-based Regularization with a Lagrangian Dual approach for automatic hyperparameter tuning.

Styles APA, Harvard, Vancouver, ISO, etc.

Augustin, Lefèvre. « Méthodes d'apprentissage appliquées à la séparation de sources mono-canal ». Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2012. http://tel.archives-ouvertes.fr/tel-00764546.

Texte intégral

Résumé :

Étant donne un mélange de plusieurs signaux sources, par exemple un morceau et plusieurs instruments, ou un entretien radiophonique et plusieurs interlocuteurs, la séparation de source mono-canal consiste a' estimer chacun des signaux sources a' partir d'un enregistrement avec un seul microphone. Puisqu'il y a moins de capteurs que de sources, il y a a priori une infinité de solutions sans rapport avec les sources originales. Il faut alors trouver quelle information supplémentaire permet de rendre le problème bien pose. Au cours des dix dernières années, la factorisation en matrices positives (NMF) est devenue un composant majeurs des systèmes de séparation de sources. En langage profane, la NMF permet de d'écrire un ensemble de signaux audio a ́ partir de combinaisons d' éléments sonores simples (les atomes), formant un dictionnaire. Les systèmes de séparation de sources reposent alors sur la capacité a trouver des atomes qui puissent être assignes de fa con univoque 'a chaque source sonore. En d'autres termes, ils doivent être interprétables. Nous proposons dans cette thèse trois contributions principales aux méthodes d'apprentissage de dictionnaire. La première est un critère de parcimonie par groupes adapte a la NMF lorsque la mesure de distorsion choisie est la divergence d'Itakura-Saito. Dans la plupart des signaux de musique on peut trouver de longs intervalles ou' seulement une source est active (des soli). Le critère de parcimonie par groupe que nous proposons permet de trouver automatiquement de tels segments et d'apprendre un dictionnaire adapte a chaque source. Ces dictionnaires permettent ensuite d'effectuer la tache de séparation dans les intervalles ou' les sources sont mélangées. Ces deux taches d'identification et de séparation sont effectuées simultanément en une seule passe de l'algorithme que nous proposons. Notre deuxième contribution est un algorithme en ligne pour apprendre le dictionnaire a grande échelle, sur des signaux de plusieurs heures, ce qui était impossible auparavant. L'espace mémoire requis par une NMF estimée en ligne est constant alors qu'il croit linéairement avec la taille des signaux fournis dans la version standard, ce qui est impraticable pour des signaux de plus d'une heure. Notre troisième contribution touche a' l'interaction avec l'utilisateur. Pour des signaux courts, l'apprentissage aveugle est particulièrement difficile, et l'apport d'information spécifique au signal traite est indispensable. Notre contribution est similaire à l'inpainting et permet de prendre en compte des annotations temps-fréquence. Elle repose sur l'observation que la quasi-totalite du spectro- gramme peut être divise en régions spécifiquement assignées a' chaque source. Nous d'éecrivons une extension de NMF pour prendre en compte cette information et discutons la possibilité d'inférer cette information automatiquement avec des outils d'apprentissage statistique simples.

Styles APA, Harvard, Vancouver, ISO, etc.

Plus de sources

Livres sur le sujet "Machine Learning Informé"

Interpretable Machine Learning for the Analysis, Design, Assessment, and Informed Decision Making for Civil Infrastructure. Elsevier Science & Technology, 2023.

Trouver le texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Madhu, G., Sandeep Kautish, A. Govardhan et Avinash Sharma, dir. Emerging Computational Approaches in Telehealth and Telemedicine : A Look at The Post-COVID-19 Landscape. BENTHAM SCIENCE PUBLISHERS, 2022. http://dx.doi.org/10.2174/97898150792721220101.

Texte intégral

Résumé :

This book gives an overview of innovative approaches in telehealth and telemedicine. The Goal of the content is to inform readers about recent computer applications in e-health, including Internet of Things (IoT) and Internet of Medical Things (IoMT) technology. The 9 chapters will guide readers to determine the urgency to intervene in specific medical cases, and to assess risk to healthcare workers. The focus on telehealth along with telemedicine, encompasses a broader spectrum of remote healthcare services for the reader to understand. Chapters cover the following topics: - A COVID-19 care system for virus precaution, prevention, and treatment - The Internet of Things (IoT) in Telemedicine, - Artificial Intelligence for Remote Patient Monitoring systems - Machine Learning in Telemedicine - Convolutional Neural Networks for the detection and prediction of melanoma in skin lesions - COVID-19 virus contact tracing via mobile apps - IoT and Cloud convergence in healthcare - Lung cancer classification and detection using deep learning - Telemedicine in India This book will assist students, academics, and medical professionals in learning about cutting-edge telemedicine technologies. It will also inform beginner researchers in medicine about upcoming trends, problems, and future research paths in telehealth and telemedicine for infectious disease control and cancer diagnosis.

Styles APA, Harvard, Vancouver, ISO, etc.

Smith, Gary, et Jay Cordes. The 9 Pitfalls of Data Science. Oxford University Press, 2019. http://dx.doi.org/10.1093/oso/9780198844396.001.0001.

Texte intégral

Résumé :

Scientific rigor and critical thinking skills are indispensable in this age of big data because machine learning and artificial intelligence are often led astray by meaningless patterns. The 9 Pitfalls of Data Science is loaded with entertaining real-world examples of both successful and misguided approaches to interpreting data, both grand successes and epic failures. Anyone can learn to distinguish between good data science and nonsense. We are confident that readers will learn how to avoid being duped by data, and make better, more informed decisions. Whether they want to be effective creators, interpreters, or users of data, they need to know the nine pitfalls of data science.

Styles APA, Harvard, Vancouver, ISO, etc.

Anderson, Raymond A. Credit Intelligence & ; Modelling. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780192844194.001.0001.

Texte intégral

Résumé :

This book, “Forest Paths” for short, started as a detailed guide for the construction of predictive models for credit and other risk assessment, for use in big-bank retail lending. It became a textbook covering credit processes (from marketing through to fraud), bureau and rating agencies, and various tools. Included are detailed histories (economics, statistics, social science}, which much referencing. It is unique in the field, with chatpers’-end questions. The primary target market is corporate and academic, but much would be of interest to a broader audience. There are eight modules: 1) an introduction to credit risk assessment and predictive modelling; 2) micro-histories of credit, credit intelligence, credit scoring, plus industrial revolutions, economic ups and downs, and both personal registration and identification; 4) mathematical and statistical tools used to develop and assess predictive models; 5) project management and data assembly; 6) data preparation from sampling to reject inference; 7) model training through to implementation; and 8) appendices, including an extensive glossary, bibliography, and index. Although the focus is credit risk, especially in the retail consumer and small-business segments, many concepts are common across disciplines as diverse as psychology, biology, engineering, and computer science, whether academic research or practical use. It also covers issues relating to the use of machine learning for credit risk assessment. Most of the focus is on traditional modelling techniques, but the increasing use of machine learning is recognised, as are its limitations. It is hoped that the contents will inform both camps.

Styles APA, Harvard, Vancouver, ISO, etc.

El-Nasr, Magy Seif, Alessandro Canossa, Truong-Huy D. Nguyen et Anders Drachen. Game Data Science. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780192897879.001.0001.

Texte intégral

Résumé :

This book is aimed at giving readers an introduction to the practical side of game data science and thus can be used a textbook for game analytics or game user research class or as a reference to self learners and enthusiasts. Game data science is a term that we use to denote a process composed of methods and techniques by which an analyst or a data scientist can make sense of data to allow decision makers in a game company to make informed decisions. This process involves: statistical analysis, visualization, abstraction of low-level data, machine learning and sequence data modeling. The book introduces different methods borrowing from different fields including human computer interaction, machine learning, and data science, focusing on methods and techniques used by both industry and researchers within the field of games. The book examples and case studies specifically focus on gameplay log data. The book takes a practical stance on the subject by discussing theoretical foundation, practical approaches, and delves deeply into the different techniques proposed and used through labs, examples, and comprehensive surveys of various case studies from both industry and academia. Topics range from simple approaches to more advanced ones. No prior knowledge is required. The book is developed to be self contained and can be used as a good way to introduce the reader to data science and how it is applied to the filed of games.

Styles APA, Harvard, Vancouver, ISO, etc.

Dowd, Cate. Digital Journalism, Drones, and Automation. Oxford University Press, 2020. http://dx.doi.org/10.1093/oso/9780190655860.001.0001.

Texte intégral

Résumé :

Advances in online technology and news systems, such as automated reasoning across digital resources and connectivity to cloud servers for storage and software, have changed digital journalism production and publishing methods. Integrated media systems used by editors are also conduits to search systems and social media, but the lure of big data and rise in fake news have fragmented some layers of journalism, alongside investments in analytics and a shift in the loci for verification. Data has generated new roles to exploit data insights and machine learning methods, but access to big data and data lakes is so significant it has spawned newsworthy partnerships between media moguls and social media entrepreneurs. However, digital journalism does not even have its own semantic systems that could protect the values of journalism, but relies on the affordances of other systems. Amidst indexing and classification systems for well-defined vocabulary and concepts in news, data leaks and metadata present challenges for journalism. By contrast data visualisations and real-time field reporting with short-form mobile media and civilian drones set new standards during the European asylum seeker crisis. Aerial filming with drones also adds to the ontological base of journalism. An ontology for journalism and intersecting ontologies can inform the design of new semantic learning systems. The Semantic CAT Method, which draws on participatory design and game design, also assists the conceptual design of synthetic players with emotion attributes, towards a meta-model for learning. The design of context-aware sensor systems to protect journalists in conflict zones is also discussed.

Styles APA, Harvard, Vancouver, ISO, etc.

Oulasvirta, Antti, Per Ola Kristensson, Xiaojun Bi et Andrew Howes, dir. Computational Interaction. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780198799603.001.0001.

Texte intégral

Résumé :

This book presents computational interaction as an approach to explaining and enhancing the interaction between humans and information technology. Computational interaction applies abstraction, automation, and analysis to inform our understanding of the structure of interaction and also to inform the design of the software that drives new and exciting human-computer interfaces. The methods of computational interaction allow, for example, designers to identify user interfaces that are optimal against some objective criteria. They also allow software engineers to build interactive systems that adapt their behaviour to better suit individual capacities and preferences. Embedded in an iterative design process, computational interaction has the potential to complement human strengths and provide methods for generating inspiring and elegant designs. Computational interaction does not exclude the messy and complicated behaviour of humans, rather it embraces it by, for example, using models that are sensitive to uncertainty and that capture subtle variations between individual users. It also promotes the idea that there are many aspects of interaction that can be augmented by algorithms. This book introduces computational interaction design to the reader by exploring a wide range of computational interaction techniques, strategies and methods. It explains how techniques such as optimisation, economic modelling, machine learning, control theory, formal methods, cognitive models and statistical language processing can be used to model interaction and design more expressive, efficient and versatile interaction.

Styles APA, Harvard, Vancouver, ISO, etc.

Giudici, Paolo, et Giulio Mignola. Big Data & ; Advanced Analytics per il Risk Management. AIFIRM, 2022. http://dx.doi.org/10.47473/2016ppa00035.

Texte intégral

Résumé :

One of the main consequences of the digital revolution, which for the last few years has been transforming almost every economic activity, has been an unprecedented availability of big data. At the same time, recent technological breakthroughs have provided tools (technological infrastructures and analytical methodologies) capable of processing these large amounts of data in a very short timeframe. Against this backdrop, the introduction of machine-learning models has been spreading. Even the Banking and Insurance sectors, despite their long-standing tradition of using statistical models, have been deeply transformed. Such an unprecedented combination of data availability, processing capabilities, and analytical models allows financial institutions to realize value by providing a more informed, timely, and conscious decision-making. The objective of this position paper is to provide the Risk Management community a useful contribution to understand the state of the art in the field of Big Data & Advanced Analytics (BD&AA) for Risk Management. To this end, the paper avails itself of contributions coming from a wide, qualified and, at the same time, heterogeneous (by origin, background, and size of the institution to which they belong) parterre of colleagues and experts.

Styles APA, Harvard, Vancouver, ISO, etc.

Dobson, James E. Critical Digital Humanities. University of Illinois Press, 2019. http://dx.doi.org/10.5622/illinois/9780252042270.001.0001.

Texte intégral

Résumé :

This book seeks to develop an answer to the major question arising from the adoption of sophisticated data-science approaches within humanities research: are existing humanities methods compatible with computational thinking? Data-based and algorithmically powered methods present both new opportunities and new complications for humanists. This book takes as its founding assumption that the exploration and investigation of texts and data with sophisticated computational tools can serve the interpretative goals of humanists. At the same time, it assumes that these approaches cannot and will not obsolete other existing interpretive frameworks. Research involving computational methods, the book argues, should be subject to humanistic modes that deal with questions of power and infrastructure directed toward the field’s assumptions and practices. Arguing for a methodologically and ideologically self-aware critical digital humanities, the author contextualizes the digital humanities within the larger neo-liberalizing shifts of the contemporary university in order to resituate the field within a theoretically informed tradition of humanistic inquiry. Bringing the resources of critical theory to bear on computational methods enables humanists to construct an array of compelling and possible humanistic interpretations from multiple dimensions—from the ideological biases informing many commonly used algorithms to the complications of a historicist text mining, from examining the range of feature selection for sentiment analysis to the fantasies of human subjectless analysis activated by machine learning and artificial intelligence.

Styles APA, Harvard, Vancouver, ISO, etc.

Chapitres de livres sur le sujet "Machine Learning Informé"

Neuer, Marcus J. « Physics-Informed Learning ». Dans Machine Learning for Engineers, 173–208. Berlin, Heidelberg : Springer Berlin Heidelberg, 2024. http://dx.doi.org/10.1007/978-3-662-69995-9_6.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Braga-Neto, Ulisses. « Physics-Informed Machine Learning ». Dans Fundamentals of Pattern Recognition and Machine Learning, 293–324. Cham : Springer International Publishing, 2024. http://dx.doi.org/10.1007/978-3-031-60950-3_12.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Wang, Sifan, et Paris Perdikaris. « Adaptive Training Strategies for Physics-Informed Neural Networks ». Dans Knowledge-Guided Machine Learning, 133–60. Boca Raton : Chapman and Hall/CRC, 2022. http://dx.doi.org/10.1201/9781003143376-6.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Simm, Jaak, Adam Arany, Edward De Brouwer et Yves Moreau. « Expressive Graph Informer Networks ». Dans Machine Learning, Optimization, and Data Science, 198–212. Cham : Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-95470-3_15.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Afroze, Lameya, Silke Merkelbach, Sebastian von Enzberg et Roman Dumitrescu. « Domain Knowledge Injection Guidance for Predictive Maintenance ». Dans Machine Learning for Cyber-Physical Systems, 75–87. Cham : Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-47062-2_8.

Texte intégral

Résumé :

AbstractWith the integration of Industry 4.0 technologies, overall maintenance costs of industrial machines can be reduced by applying predictive maintenance. Unique challenges that often occur in real-time manufacturing environments require the use of domain knowledge from different experts. However, there is hardly any guidance that suggests data scientists how to inject knowledge from predictive maintenance use cases in machine learning models. This paper addresses this lack and presents a guidance for the injection of domain knowledge in machine learning models for predictive maintenance by analyzing 50 use cases from the literature. The guidance is based on the informed machine learning framework by von Rueden et al. [1]. Finally, the guidance gives a recommendation to data scientists on how domain knowledge can be injected into different phases of model development and suggests promising machine learning models for specific use cases. The guidance is applied exemplarily to two predictive maintenance use cases.

Styles APA, Harvard, Vancouver, ISO, etc.

Sun, Alexander Y., Hongkyu Yoon, Chung-Yan Shih et Zhi Zhong. « Applications of Physics-Informed Scientific Machine Learning in Subsurface Science : A Survey ». Dans Knowledge-Guided Machine Learning, 111–32. Boca Raton : Chapman and Hall/CRC, 2022. http://dx.doi.org/10.1201/9781003143376-5.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Dani, Harsh, Jundong Li et Huan Liu. « Sentiment Informed Cyberbullying Detection in Social Media ». Dans Machine Learning and Knowledge Discovery in Databases, 52–67. Cham : Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-71249-9_4.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Mumtaz, Zahid. « Machine Learning-Based Approach for Exploring the Household Survey Data ». Dans Informal Social Protection and Poverty, 141–200. Singapore : Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-6474-9_7.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Cross, Elizabeth J., S. J. Gibson, M. R. Jones, D. J. Pitchforth, S. Zhang et T. J. Rogers. « Physics-Informed Machine Learning for Structural Health Monitoring ». Dans Structural Integrity, 347–67. Cham : Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-81716-9_17.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Sudarshan, Viswanath P., K. Pavan Kumar Reddy, Mohana Singh, Jayavardhana Gubbi et Arpan Pal. « Uncertainty-Informed Bayesian PET Image Reconstruction Using a Deep Image Prior ». Dans Machine Learning for Medical Image Reconstruction, 145–55. Cham : Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-17247-2_15.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Actes de conférences sur le sujet "Machine Learning Informé"

Oneto, Luca, Nicolò Navarin, Alessio Micheli, Luca Pasa, Claudio Gallicchio, Davide Bacciu et Davide Anguita. « Informed Machine Learning for Complex Data ». Dans ESANN 2024, 1–10. Louvain-la-Neuve (Belgium) : Ciaco - i6doc.com, 2024. http://dx.doi.org/10.14428/esann/2024.es2024-1.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Oneto, Luca, Davide Anguita et Sandro Ridella. « Informed Machine Learning : Excess Risk and Generalization ». Dans ESANN 2024, 11–16. Louvain-la-Neuve (Belgium) : Ciaco - i6doc.com, 2024. http://dx.doi.org/10.14428/esann/2024.es2024-20.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Farlessyost, William, et Shweta Singh. « Improving Mechanistic Model Accuracy with Machine Learning Informed Physics ». Dans Foundations of Computer-Aided Process Design, 275–82. Hamilton, Canada : PSE Press, 2024. http://dx.doi.org/10.69997/sct.121371.

Texte intégral

Résumé :

Machine learning presents opportunities to improve the scale-specific accuracy of mechanistic models in a data-driven manner. Here we demonstrate the use of a machine learning technique called Sparse Identification of Nonlinear Dynamics (SINDy) to improve a simple mechanistic model of algal growth. Time-series measurements of the microalga Chlorella Vulgaris were generated under controlled photobioreactor conditions at the University of Technology Sydney. A simple mechanistic growth model based on intensity of light and temperature was integrated over time and compared to the time-series data. While the mechanistic model broadly captured the overall growth trend, discrepancies remained between the model and data due to the model's simplicity and non-ideal behavior of real-world measurement. SINDy was applied to model the residual error by identifying an error derivative correction term. Addition of this SINDy-informed error dynamics term shows improvement to model accuracy while maintaining interpretability of the underlying mechanistic framework. This work demonstrates the potential for machine learning techniques like SINDy to aid simple mechanistic models in scale-specific predictive accuracy.

Styles APA, Harvard, Vancouver, ISO, etc.

Zhu, Shijie, Hao Li, Yejie Jiang et Yingjun Deng. « Inner Defect Detection via Physics-Informed Machine Learning ». Dans 2024 6th International Conference on System Reliability and Safety Engineering (SRSE), 212–16. IEEE, 2024. https://doi.org/10.1109/srse63568.2024.10772527.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Yu, Yue, Jiageng Tong, Jinhui Xia, Jinya Su et Shihua Li. « PMSM System Identification by Knowledge-informed Machine Learning ». Dans 2024 IEEE 22nd International Conference on Industrial Informatics (INDIN), 1–6. IEEE, 2024. https://doi.org/10.1109/indin58382.2024.10774223.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Zhang, Tianren, Yuanbin Wang, Ruizhe Dong, Wenhu Wang, Zhongxue Yang et Mingzhu Zhu. « Informed Machine Learning for Real-time Grinding Force Prediction ». Dans 2024 30th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), 1–6. IEEE, 2024. http://dx.doi.org/10.1109/m2vip62491.2024.10746047.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Surner, Martin, et Abdelmajid Khelil. « CIML-R : Causally Informed Machine Learning Based on Feature Relevance ». Dans 2024 11th IEEE Swiss Conference on Data Science (SDS), 68–75. IEEE, 2024. http://dx.doi.org/10.1109/sds60720.2024.00018.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Filipovic, Lado, Tobias Reiter, Julius Piso et Roman Kostal. « Equipment-Informed Machine Learning-Assisted Feature-Scale Plasma Etching Model ». Dans 2024 International Conference on Simulation of Semiconductor Processes and Devices (SISPAD), 1–4. IEEE, 2024. http://dx.doi.org/10.1109/sispad62626.2024.10733099.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Ito, Rikuto, Yasuhiro Oikawa et Kenji Ishikawa. « Tomographic Reconstruction of Sound Field From Optical Projections Using Physics-Informed Neural Networks ». Dans 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), 1–6. IEEE, 2024. http://dx.doi.org/10.1109/mlsp58920.2024.10734743.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Wade, Daniel, Hieu Ngo, Frances Love, Jeremy Partain, Andrew Wilson, Matthew Statham et Perumal Shanthakumaran. « Measurement of Vibration Transfer Functions to Inform Machine Learning Based HUMS Diagnostics ». Dans Vertical Flight Society 72nd Annual Forum & Technology Display, 1–14. The Vertical Flight Society, 2016. http://dx.doi.org/10.4050/f-0072-2016-11479.

Texte intégral

Résumé :

The US Army has improved a method for accelerating the maturity of vibration-based mechanical diagnostics, by measuring the Frequency Response Functions (FRFs) between potential failure locations and sensor locations within epicyclic gearboxes, and by building Condition Indicators (CIs) using these FRFs. The previous FRF methodology has been expanded to include frequencies up to 100 kHz, using the piezo-exciters, aircraft-installed Health and Usage Monitoring Systems (HUMS), and custom data acquisition hardware described herein. Previous CI development methodology has been improved by filtering captured vibration data with the FRFs. Using a recent process for generating diagnostic algorithms using machine learning, these FRF-based CIs outperform conventional CIs, and meet Aeronautical Design Standard 79D diagnostic classification criteria for use on board aircraft.

Styles APA, Harvard, Vancouver, ISO, etc.

Rapports d'organisations sur le sujet "Machine Learning Informé"

Martinez, Carianne, Jessica Jones, Drew Levin, Nathaniel Trask et Patrick Finley. Physics-Informed Machine Learning for Epidemiological Models. Office of Scientific and Technical Information (OSTI), octobre 2020. http://dx.doi.org/10.2172/1706217.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

McDermott, Jason, Song Feng, Christine Chang, Darren Schmidt et Vincent Danna. Structural- and Functional-Informed Machine Learning for Protein Function Prediction. Office of Scientific and Technical Information (OSTI), septembre 2021. http://dx.doi.org/10.2172/1988630.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Guthrie, George Drake Jr, et Hari S. Viswanathan. Science-informed Machine Learning to Increase Recovery Efficiency in Unconventional Reservoirs. Office of Scientific and Technical Information (OSTI), avril 2020. http://dx.doi.org/10.2172/1614818.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Wang, Jianxun, Jinlong Wu, Julia Ling, Gianluca Iaccarino et Heng Xiao. Physics-Informed Machine Learning for Predictive Turbulence Modeling : Towards a Complete Framework. Office of Scientific and Technical Information (OSTI), septembre 2016. http://dx.doi.org/10.2172/1562229.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Bailey Bond, Robert, Pu Ren, James Fong, Hao Sun et Jerome F. Hajjar. Physics-informed Machine Learning Framework for Seismic Fragility Analysis of Steel Structures. Northeastern University, août 2024. http://dx.doi.org/10.17760/d20680141.

Texte intégral

Résumé :

The seismic assessment of structures is a critical step to increase community resilience under earthquake hazards. This research aims to develop a Physics-reinforced Machine Learning (PrML) paradigm for metamodeling of nonlinear structures under seismic hazards using artificial intelligence. Structural metamodeling, a reduced-fidelity surrogate model to a more complex structural model, enables more efficient performance-based design and analysis, optimizing structural designs and ease the computational effort for reliability fragility analysis, leading to globally efficient designs while maintaining required levels of accuracy. The growing availability of high-performance computing has improved this analysis by providing the ability to evaluate higher order numerical models. However, more complex models of the seismic response of various civil structures demand increasing amounts of computing power. In addition, computational cost greatly increases with numerous iterations to account for optimization and stochastic loading (e.g., Monte Carlo simulations or Incremental Dynamic Analysis). To address the large computational burden, simpler models are desired for seismic assessment with fragility analysis. Physics reinforced Machine Learning integrates physics knowledge (e.g., scientific principles, laws of physics) into the traditional machine learning architectures, offering physically bounded, interpretable models that require less data than traditional methods. This research introduces a PrML framework to develop fragility curves using the combination of neural networks of domain knowledge. The first aim involves clustering and selecting ground motions for nonlinear response analysis of archetype buildings, ensuring that selected ground motions will include as few ground motions as possible while still expressing all the key representative events the structure will probabilistically experience in its lifetime. The second aim constructs structural PrML metamodels to capture the nonlinear behavior of these buildings utilizing the nonlinear Equation of Motion (EOM). Embedding physical principles, like the general form of the EOM, into the learning process will inform the system to stay within known physical bounds, resulting in interpretable results, robust inferencing, and the capability of dealing with incomplete and scarce data. The third and final aim applies the metamodels to probabilistic seismic response prediction, fragility analysis, and seismic performance factor development. The efficiency and accuracy of this approach are evaluated against existing physics-based fragility analysis methods.

Styles APA, Harvard, Vancouver, ISO, etc.

Mueller, Juliane. Machine Learning to Enable Efficient Uncertainty Quantification, Data Assimilation, and Informed Data Acquisition. Office of Scientific and Technical Information (OSTI), mars 2021. http://dx.doi.org/10.2172/1769743.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Athon, Matthew, Danielle Ciesielski, Jordan Corbey, Shenyang Hu, Ethan King, Yulan Li, Jacqueline Royer, Panagiotis Stinis, Robert Surbella et Scott Swenson. Visualizing Uranium Crystallization from Melt : Experiment-Informed Phase Field Modeling and Machine Learning. Office of Scientific and Technical Information (OSTI), septembre 2023. http://dx.doi.org/10.2172/2338176.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Ullrich, Paul, Tapio Schneider et Da Yang. Physics-Informed Machine Learning from Observations for Clouds, Convection, and Precipitation Parameterizations and Analysis. Office of Scientific and Technical Information (OSTI), avril 2021. http://dx.doi.org/10.2172/1769762.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Ghanshyam, Pilania, Kenneth James McClellan, Christopher Richard Stanek et Blas P. Uberuaga. Physics-Informed Machine Learning for Discovery and Optimization of Materials : A Case Study of Scintillators. Office of Scientific and Technical Information (OSTI), août 2018. http://dx.doi.org/10.2172/1463529.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Bao, Jie, Chao Wang, Zhijie Xu et Brian J. Koeppel. Physics-Informed Machine Learning with Application to Solid Oxide Fuel Cell System Modeling and Optimization. Office of Scientific and Technical Information (OSTI), septembre 2019. http://dx.doi.org/10.2172/1569289.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Nous offrons des réductions sur tous les plans premium pour les auteurs dont les œuvres sont incluses dans des sélections littéraires thématiques. Contactez-nous pour obtenir un code promo unique!