Exploració per autor "Romero Merino, Enrique"
Ara es mostren els items 28-47 de 52
-
Learning with Feed-forward Neural Networks: Three Schemes to Deal with the Bias/Variance Trade-off
(Universitat Politècnica de Catalunya, 2004-11-30)
Tesi
Accés obertIn terms of the Bias/Variance decomposition, very flexible (i.e., complex) Supervised Machine Learning systems may lead to unbiased estimators but with high variance. A rigid model, in contrast, may lead to small variance ... -
Male and female politicians on Twitter: A machine learning approach
(2021-02)
Article
Accés obertHow does the language of male and female politicians differ when they communicate directly with the public on social media? Do citizens address them differently? We apply Lasso logistic regression models to identify the ... -
MALEAD: Machine learning in architecture design
(2023)
Article
Accés obert -
Margin maximization with feed-forward neural networks: a comparative study with support vector machines and AdaBoost
(2003-06)
Report de recerca
Accés obertFeed-forward Neural Networks (FNN) and Support Vector Machines (SVM) are two machine learning frameworks developed from very different starting points of view. In this work a new learning model for FNN is proposed such ... -
Maximizing the margin with feed-forward neural networks
(2001-07)
Report de recerca
Accés obertFeed-forward Neural Networks (FNNs) and Support Vector Machines (SVMs) are two machine learning frameworks developed from very different starting points of view. The solutions obtained by the respective frameworks may ... -
Modeling perceptual categories of parametric musical systems
(Elsevier, 2017-07-11)
Article
Accés obertIn computer music fields, such as algorithmic composition and live coding, the aural exploration of parameter combinations is the process through which systems’ capabilities are learned and the material for different musical ... -
Neighborhood-based stopping criterion for contrastive divergence
(2018-07)
Article
Accés obertRestricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence (CD) learning algorithm, an ... -
Neural networks with periodic and monotonic activation functions: a comparative study in classification problems
(2000-02)
Report de recerca
Accés obertThis article discusses a number of reasons why the use of non-monotonic functions as activation functions can lead to a marked improvement in the performance of a neural network. Using a wide range of benchmarks we show ... -
NMF for quality control of multi-modal retinal images for diagnosis of diabetes mellitus and diabetic retinopathy
(Springer, 2022)
Text en actes de congrés
Accés obertIn current ophthalmology, images of the vascular system in the human retina are used as exploratory proxies for pathologies affecting different organs. In this brief paper, we use multi-modal retinal images for assisting ... -
On the selection of hidden neurons with heuristic search strategies for approximation
(2006)
Text en actes de congrés
Accés obertFeature Selection techniques usually follow some search strategy to select a suitable subset from a set of features. Most neural network growing algorithms perform a search with Forward Selection with the objective of ... -
On the use of pairwise distance learning for brain signal classification with limited observations
(2020-05)
Article
Accés obertThe increasing access to brain signal data using electroencephalography creates new opportunities to study electrophysiological brain activity and perform ambulatory diagnoses of neurological disorders. This work proposes ... -
On-the-fly syntheziser programming with fuzzy rule learning
(2020-08-31)
Article
Accés obertThis manuscript explores fuzzy rule learning for sound synthesizer programming within the performative practice known as live coding. In this practice, sound synthesis algorithms are programmed in real time by means of ... -
Preprocessing MRS information for classification of human brain tumours
(IGI Global, 2012-06)
Capítol de llibre
Accés restringit per política de l'editorial -
Radiomics-based assessment of optical coherence tomography angiography images for diabetic retinopathy diagnosis
(Elsevier, 2023-06)
Article
Accés obertPurpose: To evaluate the diagnostic accuracy of machine learning (ML) techniques applied to radiomic features extracted from OCT and OCT angiography (OCTA) images for diabetes mellitus (DM), diabetic retinopathy (DR), and ... -
Screening dyslexia for English using HCI measures and machine learning
(Association for Computing Machinery (ACM), 2018)
Text en actes de congrés
Accés obertMore than 10% of the population has dyslexia, and most are diagnosed only after they fail in school. This work seeks to change this through early detection via machine learning models that predict dyslexia by observing how ... -
Search strategies guided by the evidence for the selection of basis functions in regression
(Institute of Electrical and Electronics Engineers (IEEE), 2007)
Text en actes de congrés
Accés obertThis work addresses the problem of selecting a subset of basis functions for a model linear in the parameters for regression tasks. Basis functions from a set of candidates are explicitly selected with search methods coming ... -
Selection of basis functions guided by the L2 soft margin
(Springer, 2007)
Text en actes de congrés
Accés obertSupport Vector Machines (SVMs) for classification tasks produce sparse models by maximizing the margin. Two limitations of this technique are considered in this work: firstly, the number of support vectors can be large ... -
Sepsis mortality prediction with the Quotient Basis Kernel
(2014-05)
Article
Accés restringit per política de l'editorialObjective: This paper presents an algorithm to assess the risk of death in patients with sepsis. Sepsis is a common clinical syndrome in the intensive care unit (ICU) that can lead to severe sepsis, a severe state of septic ... -
Shear strength properties and collapse response of a sandy silt under generalized stress states
(American Society of Civil Engineers (ASCE), 2018)
Text en actes de congrés
Accés restringit per política de l'editorialThe paper presents preliminary results on the shear strength properties and collapse response of a compacted low-density mixture of fine sand and clayey silt in a hollow cylinder apparatus. Shear strength tests at two ... -
Stopping criteria in contrastive divergence: Alternatives to the reconstruction error
(2014)
Text en actes de congrés
Accés obertRestricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence learning algorithm (CD), an ...
