000			02920nam a22004215c 4500
988			_aSpringer_Robotics_2020
999			_c115342 _d115342 _x1
001			115342
003			ES-MaUEC
005			20240314180502.0
006			a||||fo|||| 00| 0
007			cr nn nnnaamaa
008			190717s2020 gw a o |||| 0|eng d
020			_a9783030243593
024	7		_a10.1007/978-3-030-24359-3 _2doi
040			_aES-MaUEC _bspa _cES-MaUEC _dES-MaUEC
050		4	_aQ325.5 _b2020 EB
100	1		_aOneto, Luca _eautor _9671761
245	1	0	_aModel selection and error estimation in a nutshell _cby Luca Oneto
250			_aFirst edition
264		1	_aCham _bSpringer International Publishing _c2020
300			_a1 recurso en línea (XIII, 132 páginas) _b62 ilustraciones
336			_2rdacontent _aTexto _btxt
337			_2rdamedia _aelectrónico _bc
338			_2rdacarrier _arecurso electrónico _bcr
347			_atext file _bPDF
490	0		_aModeling and Optimization in Science and Technologies _x2196-7326 _v15
490	0		_aIntelligent Technologies and Robotics (Springer-42732)
505	0		_aIntroduction -- The "Five W" of MS & EE -- Preliminaries -- Resampling Methods -- Complexity-Based Methods -- Compression Bound -- Algorithmic Stability Theory -- PAC-Bayes Theory -- Differential Privacy Theory -- Conclusions & Further Readings.
520	3		_aHow can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80's and includes the most recent results. It discusses open problems and outlines future directions for research.
650		7	_2embne _aAprendizaje automático _9166090
650		7	_2embne _aAlgoritmos _9141162
776	0	8	_iPrinted edition: _z9783030243586
776	0	8	_iPrinted edition: _z9783030243609
776	0	8	_iPrinted edition: _z9783030243616
856	4	0	_uhttps://go.openathens.net/redirector/universidadeuropea.es?url=https://doi.org/10.1007/978-3-030-24359-3 _zAcceso a este recurso digital (usuarios Universidad Europea de Madrid)
942			_2lcc _cLE
998			_aSI _cm _dz _feng _ggw _h0 _b12/2019 _eel _zSI