Título :	European Conference, ECML PKDD 2017, Skopje, Macedonia, September 18–22, 2017, Proceedings, Part II
Tipo de documento:	documento electrónico
Autores:	Ceci, Michelangelo, ; Hollmén, Jaakko, ; Todorovski, Ljupčo, ; Vens, Celine, ; Džeroski, Sašo,
Mención de edición:	1 ed.
Editorial:	[s.l.] : Springer
Fecha de publicación:	2017
Número de páginas:	XXXIII, 866 p. 213 ilustraciones
ISBN/ISSN/DL:	978-3-319-71246-8
Nota general:	Libro disponible en la plataforma SpringerLink. Descarga y lectura en formatos PDF, HTML y ePub. Descarga completa o por capítulos.
Palabras clave:	Procesamiento de datos  Inteligencia artificial  Visión por computador  Software de la aplicacion  Protección de datos  Ordenadores  Minería de datos y descubrimiento de conocimientos  Aplicaciones informáticas y de sistemas de información  Seguridad de datos e información  Entornos informáticos
Índice Dewey:	6.312
Resumen:	Las actas de tres volúmenes LNAI 10534 – 10536 constituyen las actas arbitradas de la Conferencia Europea sobre Aprendizaje Automático y Descubrimiento de Conocimiento en Bases de Datos, ECML PKDD 2017, celebrada en Skopje, Macedonia, en septiembre de 2017. El total de 101 artículos regulares presentados en la parte I y la parte II fue cuidadosamente revisada y seleccionada entre 364 presentaciones; Hay 47 artículos en la sección de demostración, néctar y ciencia de datos aplicada. Las contribuciones se organizaron en secciones temáticas denominadas de la siguiente manera: Parte I: detección de anomalías; visión por computador; conjuntos y metaaprendizaje; selección y extracción de características; métodos del núcleo; aprendizaje y optimización, factorización matricial y tensorial; redes y gráficos; Redes neuronales y aprendizaje profundo. Parte II: minería de patrones y secuencias; privacidad y seguridad; modelos y métodos probabilísticos; recomendación; regresión; aprendizaje reforzado; descubrimiento de subgrupos; series de tiempo y flujos; transferencia y aprendizaje multitarea; Aprendizaje no supervisado y semisupervisado. Parte III: pista de ciencia de datos aplicada; pista de néctar; y pista de demostración.
Nota de contenido:	Pattern and Sequence Mining -- BeatLex: Summarizing and Forecasting Time Series with Patterns -- Behavioral Constraint Template-Based Sequence Classification -- Efficient Sequence Regression by Learning Linear Models in All-Subsequence Space -- Subjectively Interesting Connecting Trees -- Privacy and Security -- Malware Detection by Analysing Encrypted Network Traffic with Neural Networks -- PEM: Practical Differentially Private System for Large-Scale Cross-Institutional Data Mining -- Probabilistic Models and Methods -- Bayesian Heatmaps: Probabilistic Classification with Multiple Unreliable Information Sources -- Bayesian Inference for Least Squares Temporal Difference Regularization -- Discovery of Causal Models that Contain Latent Variables through Bayesian Scoring of Independence Constraints -- Labeled DBN learning with community structure knowledge -- Multi-view Generative Adversarial Networks -- Online Sparse Collapsed Hybrid Variational-Gibbs Algorithm for Hierarchical Dirichlet Process Topic Models -- PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach -- Partial Device Fingerprints -- Robust Multi-view Topic Modeling by Incorporating Detecting Anomalies -- Recommendation -- A Regularization Method with Inference of Trust and Distrust in Recommender Systems -- A Unified Contextual Bandit Framework for Long- and Short-Term Recommendations -- Perceiving the Next Choice with Comprehensive Transaction Embeddings for Online Recommendation -- Regression -- Adaptive Skip-Train Structured Regression for Temporal Networks -- ALADIN: A New Approach for Drug-Target Interaction Prediction -- Co-Regularised Support Vector Regression -- Online Regression with Controlled Label Noise Rate -- Reinforcement Learning -- Generalized Inverse Reinforcement Learning with Linearly Solvable MDP -- Max K-armed bandit: On the ExtremeHunter algorithm and beyond -- Variational Thompson Sampling for Relational Recurrent Bandits -- Subgroup Discovery -- Explaining Deviating Subsetsthrough Explanation Networks -- Flash points: Discovering exceptional pairwise behaviors in vote or rating data -- Time Series and Streams -- A Multiscale Bezier-Representation for Time Series that Supports Elastic Matching -- Arbitrated Ensemble for Time Series Forecasting -- Cost Sensitive Time-series Classification -- Cost-Sensitive Perceptron Decision Trees for Imbalanced Drifting Data Streams -- Efficient Temporal Kernels between Feature Sets for Time Series Classification -- Forecasting and Granger modelling with non-linear dynamical dependencies -- Learning TSK Fuzzy Rules from Data Streams -- Non-Parametric Online AUC Maximization -- On-line Dynamic Time Warping for Streaming Time Series -- PowerCast: Mining and Forecasting Power Grid Sequences -- UAPD: Predicting Urban Anomalies from Spatial-Temporal Data -- Transfer and Multi-Task Learning -- A Novel Rating Pattern Transfer Model for Improving Non-Overlapping Cross-Domain Collaborative Filtering -- Distributed Multi-task Learning for SensorNetwork -- Learning task structure via sparsity grouped multitask learning -- Lifelong Learning with Gaussian Processes -- Personalized Tag Recommendation for Images Using Deep Transfer Learning -- Ranking based Multitask Learning of Scoring Functions -- Theoretical Analysis of Domain Adaptation with Optimal Transport -- TSP: Learning Task-Speci_c Pivots for Unsupervised Domain Adaptation -- Unsupervised and Semisupervised Learning -- k2-means for fast and accurate large scale clustering -- A Simple Exponential Family Framework for Zero-Shot Learning -- DeepCluster: A General Clustering Framework based on Deep Learning -- Multi-view Spectral Clustering on Conflicting Views -- Pivot-based Distributed K-Nearest Neighbor Mining.
En línea:	https://link-springer-com.biblioproxy.umanizales.edu.co/referencework/10.1007/97 [...]
Link:	https://biblioteca.umanizales.edu.co/ils/opac_css/index.php?lvl=notice_display&i

European Conference, ECML PKDD 2017, Skopje, Macedonia, September 18–22, 2017, Proceedings, Part II [documento electrónico] / Ceci, Michelangelo, ; Hollmén, Jaakko, ; Todorovski, Ljupčo, ; Vens, Celine, ; Džeroski, Sašo,  . -  1 ed.  . - [s.l.] : Springer, 2017 . - XXXIII, 866 p. 213 ilustraciones.
ISBN : 978-3-319-71246-8
Libro disponible en la plataforma SpringerLink. Descarga y lectura en formatos PDF, HTML y ePub. Descarga completa o por capítulos.

Palabras clave:	Procesamiento de datos  Inteligencia artificial  Visión por computador  Software de la aplicacion  Protección de datos  Ordenadores  Minería de datos y descubrimiento de conocimientos  Aplicaciones informáticas y de sistemas de información  Seguridad de datos e información  Entornos informáticos
Índice Dewey:	6.312
Resumen:	Las actas de tres volúmenes LNAI 10534 – 10536 constituyen las actas arbitradas de la Conferencia Europea sobre Aprendizaje Automático y Descubrimiento de Conocimiento en Bases de Datos, ECML PKDD 2017, celebrada en Skopje, Macedonia, en septiembre de 2017. El total de 101 artículos regulares presentados en la parte I y la parte II fue cuidadosamente revisada y seleccionada entre 364 presentaciones; Hay 47 artículos en la sección de demostración, néctar y ciencia de datos aplicada. Las contribuciones se organizaron en secciones temáticas denominadas de la siguiente manera: Parte I: detección de anomalías; visión por computador; conjuntos y metaaprendizaje; selección y extracción de características; métodos del núcleo; aprendizaje y optimización, factorización matricial y tensorial; redes y gráficos; Redes neuronales y aprendizaje profundo. Parte II: minería de patrones y secuencias; privacidad y seguridad; modelos y métodos probabilísticos; recomendación; regresión; aprendizaje reforzado; descubrimiento de subgrupos; series de tiempo y flujos; transferencia y aprendizaje multitarea; Aprendizaje no supervisado y semisupervisado. Parte III: pista de ciencia de datos aplicada; pista de néctar; y pista de demostración.
Nota de contenido:	Pattern and Sequence Mining -- BeatLex: Summarizing and Forecasting Time Series with Patterns -- Behavioral Constraint Template-Based Sequence Classification -- Efficient Sequence Regression by Learning Linear Models in All-Subsequence Space -- Subjectively Interesting Connecting Trees -- Privacy and Security -- Malware Detection by Analysing Encrypted Network Traffic with Neural Networks -- PEM: Practical Differentially Private System for Large-Scale Cross-Institutional Data Mining -- Probabilistic Models and Methods -- Bayesian Heatmaps: Probabilistic Classification with Multiple Unreliable Information Sources -- Bayesian Inference for Least Squares Temporal Difference Regularization -- Discovery of Causal Models that Contain Latent Variables through Bayesian Scoring of Independence Constraints -- Labeled DBN learning with community structure knowledge -- Multi-view Generative Adversarial Networks -- Online Sparse Collapsed Hybrid Variational-Gibbs Algorithm for Hierarchical Dirichlet Process Topic Models -- PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach -- Partial Device Fingerprints -- Robust Multi-view Topic Modeling by Incorporating Detecting Anomalies -- Recommendation -- A Regularization Method with Inference of Trust and Distrust in Recommender Systems -- A Unified Contextual Bandit Framework for Long- and Short-Term Recommendations -- Perceiving the Next Choice with Comprehensive Transaction Embeddings for Online Recommendation -- Regression -- Adaptive Skip-Train Structured Regression for Temporal Networks -- ALADIN: A New Approach for Drug-Target Interaction Prediction -- Co-Regularised Support Vector Regression -- Online Regression with Controlled Label Noise Rate -- Reinforcement Learning -- Generalized Inverse Reinforcement Learning with Linearly Solvable MDP -- Max K-armed bandit: On the ExtremeHunter algorithm and beyond -- Variational Thompson Sampling for Relational Recurrent Bandits -- Subgroup Discovery -- Explaining Deviating Subsetsthrough Explanation Networks -- Flash points: Discovering exceptional pairwise behaviors in vote or rating data -- Time Series and Streams -- A Multiscale Bezier-Representation for Time Series that Supports Elastic Matching -- Arbitrated Ensemble for Time Series Forecasting -- Cost Sensitive Time-series Classification -- Cost-Sensitive Perceptron Decision Trees for Imbalanced Drifting Data Streams -- Efficient Temporal Kernels between Feature Sets for Time Series Classification -- Forecasting and Granger modelling with non-linear dynamical dependencies -- Learning TSK Fuzzy Rules from Data Streams -- Non-Parametric Online AUC Maximization -- On-line Dynamic Time Warping for Streaming Time Series -- PowerCast: Mining and Forecasting Power Grid Sequences -- UAPD: Predicting Urban Anomalies from Spatial-Temporal Data -- Transfer and Multi-Task Learning -- A Novel Rating Pattern Transfer Model for Improving Non-Overlapping Cross-Domain Collaborative Filtering -- Distributed Multi-task Learning for SensorNetwork -- Learning task structure via sparsity grouped multitask learning -- Lifelong Learning with Gaussian Processes -- Personalized Tag Recommendation for Images Using Deep Transfer Learning -- Ranking based Multitask Learning of Scoring Functions -- Theoretical Analysis of Domain Adaptation with Optimal Transport -- TSP: Learning Task-Speci_c Pivots for Unsupervised Domain Adaptation -- Unsupervised and Semisupervised Learning -- k2-means for fast and accurate large scale clustering -- A Simple Exponential Family Framework for Zero-Shot Learning -- DeepCluster: A General Clustering Framework based on Deep Learning -- Multi-view Spectral Clustering on Conflicting Views -- Pivot-based Distributed K-Nearest Neighbor Mining.
En línea:	https://link-springer-com.biblioproxy.umanizales.edu.co/referencework/10.1007/97 [...]
Link:	https://biblioteca.umanizales.edu.co/ils/opac_css/index.php?lvl=notice_display&i