Feature Learning and Understanding [[electronic resource] ] : Algorithms and Applications / / by Haitao Zhao, Zhihui Lai, Henry Leung, Xianyi Zhang

• Autore: Zhao Haitao
• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2020
• Edizione: 1st ed. 2020.
• Descrizione fisica: 1 online resource (XIV, 291 p. 126 illus., 109 illus. in color.)
• Disciplina: 006.31
• Soggetto topico: Sociophysics; Econophysics; Machine learning; Computational intelligence; Pattern recognition; Signal processing; Image processing; Speech processing systems; Optical data processing; Data-driven Science, Modeling and Theory Building; Machine Learning; Computational Intelligence; Pattern Recognition; Signal, Image and Speech Processing; Image Processing and Computer Vision
• Persona (resp. second.): LaiZhihui; LeungHenry; ZhangXianyi
• Nota di contenuto: Chapter1. A Gentle Introduction to Feature Learning -- Chapter2. Latent Semantic Feature Learning -- Chapter3. Principal Component Analysis -- Chapter4. Local-Geometrical-Structure-based Feature Learning -- Chapter5. Linear Discriminant Analysis -- Chapter6. Kernel-based nonlinear feature learning -- Chapter7. Sparse feature learning -- Chapter8. Low rank feature learning -- Chapter9. Tensor-based Feature Learning -- Chapter10. Neural-network-based Feature Learning: Autoencoder -- Chapter11. Neural-network-based Feature Learning: Convolutional Neural Network -- Chapter12. Neural-network-based Feature Learning: Recurrent Neural Network.
• Sommario/riassunto: This book covers the essential concepts and strategies within traditional and cutting-edge feature learning methods thru both theoretical analysis and case studies. Good features give good models and it is usually not classifiers but features that determine the effectiveness of a model. In this book, readers can find not only traditional feature learning methods, such as principal component analysis, linear discriminant analysis, and geometrical-structure-based methods, but also advanced feature learning methods, such as sparse learning, low-rank decomposition, tensor-based feature extraction, and deep-learning-based feature learning. Each feature learning method has its own dedicated chapter that explains how it is theoretically derived and shows how it is implemented for real-world applications. Detailed illustrated figures are included for better understanding. This book can be used by students, researchers, and engineers looking for a reference guide for popular methods of feature learning and machine intelligence.
• Titolo autorizzato: Feature Learning and Understanding
• ISBN: 3-030-40794-2
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996418174703316
• Lo trovi qui: Univ. di Salerno
• Serie: Information Fusion and Data Science, . 2510-1528