Semantic Scholar extracted view of "An experimental comparison of performance measures for classification" by C. Ferri et al. Skip to search form Skip ...
The usefulness and evaluation of "cautious" or "partial" classifiers is pursued, and ROC analysis and AUC evaluations are extended to these classifiers, by considering the degree of abstention as an additional dimension. The evaluation and use of classifiers is based on the idea that a classifier is defined as a complete function from instances to classes. …
This short report includes a summary of the presentations and discussions held during the ROCAI-2004 workshop, as well as the workshop conclusions and the future agenda. This short report includes a summary of the presentations and discussions held during the ROCAI-2004 workshop, as well as the workshop conclusions and the future agenda. …
The area under the ROC curve (AUC), a well-known measure of ranking performance, is also often used as a measure of classification performance, aggregating …
Hernández-Orallo, J., Flach, P., & Ferri, C. (2011). Brier curves: a new cost-based visualisation of classifier performance . In Proceedings of the 28th International …
Semantic Scholar profile for C. Ferri, with 215 highly influential citations and 144 scientific research papers. Skip to search form Skip to main content Skip to account menu. Semantic Scholar's Logo. Search 214,622,808 papers from all fields of science ... J. Hernández-Orallo Peter A. Flach C. Ferri. Computer Science.
Existen diferentes tareas de la minería de datos tales como clasificación, regresión, agrupamiento, correlación y reglas de asociación (Hernández Orallo et al., 2004; Witten et al., 2016 ...
This alert has been successfully added and will be sent to: You will be notified whenever a record that you have chosen has been cited.
La ILP ha significado un importante salto cuali-tativo in el campo del aprendizaje automático ya that posee una expresividad mayor que los tradicionale marcos proposicionales. La programación lógica inductiva (ILP) [9] es un marco para la inferencia inductiva de teorías de primer orden a partir de hechos. El uso de la programación lógica para el aprendizaje …
author:j-hernandez-orallo - Google Scholar 2 of 15 10/01/2008 17:22 J Hernandez-Or… C Ferri P Flach M Ramírez-Quin… V Estruch [PDF] Learning decision trees using the area under the ROC curve - all 11 versions » C Ferri, P Flach, J Hernandez-Orallo - Proceedings of the 19th International Conference on Machine …, 2002 - dns2.icarr.it Page 1.
C. Ferri, P. Flach, J. Hernández-Orallo "Improving the AUC of Probabilistic Estimators Trees" in Proc. of 14th European Conference on Machine Learning, ECML'03, LNAI Springer Verlag, Vol 2837, pages 121-132, 2003.
José Hernández Orallo, María José Ramírez Quintana, César Ferri Ramírez Pearson Educación, 2004 - Computers - 680 pages El manual discurre apoyándose en numerosos ejemplos prácticos y utilizando herramientas de minería de datos como SPSS, Clementine o WEKA, ilustrando cada técnica con las diferentes implementaciones que de ella ...
In this paper we propose a more natural way of visualising classifier performance in cost space, which is to plot probabilistic loss on the y-axis, i.e., the loss …
Section 6 presents four different experiments to analyse the sensitivity of the 18 measures to the four above-mentioned traits: class threshold choice, separability/ranking quality, calibration performance and sensitivity to changes in prior class distribution. Finally, Section 7 includes the conclusions, and gives some ideas for future work.
Palabras clave: minería de datos, información criminal, patrones delictivos, clustering, clasificación ..... Comienza con una introducción a la minería de datos, luego se comenta el uso de la ... datos [Hernández Orallo, 2000]. La Minería de ... Aplicación de Minería de Datos para la Exploración y Detección de ....
José Hernández-Orallo is currently an associate professor in the department of information systems and computation at UPV. He holds a BSc and an MSc in computer science from UPV, partly completed at the École Nationale Supérieure de l'Électronique et de ses Applications (France), and a PhD in logic with a doctoral extraordinary prize from the …
A Bella, C Ferri, J Hernández-Orallo, MJ Ramirez-Quintana. 2010 IEEE International Conference on Data Mining, 737-742, 2010. 144: 2010: ROC curves for regression. J …
This chapter starts from recent results in machine teaching that show the relevance of prior alignment between humans and machines, and analyses how machine teaching relates to explainable artificial intelligence, and how simplicity priors play a role beyond intelligibility. Machine intelligence differs signficantly from human intelligence. While human …
C. Ferri, J. Hernández-Orallo, M. J. Ramírez-Quintana; Published 2013; Computer Science; TLDR. This paper overhauls this aproach in the context of a general learning framework for structured prediction using user-defined operators and a functional programming language for the representation of rules and operators for policy reuse.
Fernando Martínez-Plumed, Cèsar Ferri, José Hernández-Orallo, and María J Ramírez-Quintana. Adaptive Behavior 2015 23: 5, 283-299 Download Citation. If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and ...
Fernando Martínez-Plumed Cèsar Ferri David Nieves José Hernández-Orallo Valencian Research Institute for Artificial Intelligence (VRAIN) Universitat Politècnica de València, Spain {fmartinez,daniecor,cferri,jorallo}@dsic.upv.es May 31, 2019 ABSTRACT The causes underlying unfair decision making are complex, being …
This paper addresses the possibilities, advantages and shortcomings of addressing different data-mining problems with the Inductive Functional Logic Programming (IFLP) paradigm, and illustrates how these features are included in the IFLP paradigm and shows some results with the system FLIP. In this paper we address the possibilities, advantages and …
Antonio Bella, Cèsar Ferri, José Hernández-Orallo, and María José Ramírez-Quintana Departamento de Sistemas Informáticos y Computación Universidad Politécnica de Valencia (+34) 963877007 (ext. 73585, 73586, 83505, 73537), (+34) 963877359 {jorallo, mramirez, cferri, abella}@dsic.upv.es
A comprehensive evaluation of the retraining and reframing approaches is performed using a repository of binarised regression problems created on purpose, concluding that no method is clearly better than the other, except when the size of the training data is small. Some supervised tasks are presented with a numerical output but decisions have to be …
C. Ferri, P. Flach, J. Hernández-Orallo "Improving the AUC of Probabilistic Estimators Trees" in Proc. of 14th European Conference on Machine Learning, ECML'03, LNAI …
This work devise a new method to extract one single solution from a hypothesis ensemble without using extra data, based on two main ideas: the selected solution must be similar, semantically, to the combined solution, and this similarity is evaluated through the use of a random dataset. Ensemble methods improve accuracy by combining the predictions of a …
Introducción a la Minería de Datos José Hernández Orallo Mª José Ramírez Quintana Cèsar Ferri Ramírez Estadísticos e-Books & Papers Estadísticos e-Books & Papers Estadísticos e-Books & Papers INTRODUCCIÓN A LA MINERÍA DE DATOS HERNÁNDEZ ORALLO, J.; RAMÍREZ QUINTANA, M. J.; FERRI RAMÍREZ, C Depósito legal: SE-5115 …
Fernando Martínez-Plumed, C. Ferri, +1 author J. Hernández-Orallo; Published in arXiv 29 May 2019; Computer Science; TLDR. It is found that rows containing missing values are usually fairer than the rest, which should not be treated as the uncomfortable ugly data that different techniques and libraries get rid of at the first occasion.
Devwudfw1 Zh suhvhqw d iudphzrun iru wkh Lqgxfwlyh Ixqfwlrqdo Orjlf Surjudpplqj sdudgljp iurp srvlwlyh gdwd dqg iurp qrq0xqlirup fodvvhv1 Lw h{whqgv wkh Ed|hvldq dssurdfk lq ^4;` wr frqvlghu fodvvhv lq wkh gh ql0 wlrq ri k|srwkhvlv jhqhudolw|/ qrz fdoohg fodvv xqhyhqqhvv/ zklfk lv xvhg iru wkh hydoxdwlrq ri k|srwkhvhv1 Wklv qhz phdvxuh wdnhv …
This work shows a simple procedure that builds the witness joint distribution from the ground joint distribution, and proves a chain of relations, also with a theoretical lower bound, on the teaching dimension of the old and new models. Over the past decades in the field of machine teaching, several restrictions have been introduced to avoid …
Brier score, etc. (Hernández-Orallo et al. 2012; Flach et al. 2011; Zadrozny and Elkan 2001a;Liu et al. 2011) around c and make the decision accordingly, which we can then …
C. Ferri, J. Hernández-Orallo, M. J. Ramírez-Quintana; Published 2013; Computer Science; Policy reuse is a kind of transfer learning to improve a reinforcement learning system by reusing part of the information of the statevalue function from previous problems to new problems. In this paper we overhaul this aproach in the context of a general ...
This work considers the extension of the Inductive Functional Logic Programming (IFLP) framework in order to learn functions in an incremental way and several examples of programs which have been induced indicate that this extension pays off in practice. In this work, we consider the extension of the Inductive Functional Logic Programming (IFLP) …
José Hernández-Orallo is currently an associate professor in the department of information systems and computation at UPV. He holds a BSc and an MSc in computer science from UPV, partly completed at the École Nationale Supérieure de l'Électronique et de ses Applications (France), and a PhD in logic with a doctoral extraordinary prize from …
This paper considers the situation when the quality of features during deployment is worse than during training, and how a model will behave during deployment for different noise contexts depends on a context whose value can be known during deployment. In many machine learning applications the quality of features during deployment is worse than …
DOI: 10.1007/s10618-019-00613-7 Corpus ID: 67184677; Setting decision thresholds when operating conditions are uncertain @article{Ferri2019SettingDT, …