000			05683cam a2200433Ii 4500
001			95718
003			ES-MaUEC
005			20230102112718.0
006			m o d
007			cr cnu|||unuuu
008			170403s2017 sz a ob 001 0 eng d
020			_a3319553127 _q(electronic bk.)
020			_a9783319553122 _q(electronic bk.)
020			_z3319553119
020			_z9783319553115
040			_aN$T _cN$T _dN$T _dGW5XE _dYDX _dEBLCP _dOCLCF _dAZU _dUPM _dUAB _dESU _dIOG _dJBG _dIAD _dICW _dICN _dVT2 _dCOO _dOTZ _dOCLCQ _dU3W _dES-MaUEC _bspa
050		4	_aQ325.5 _bK855 2017 EB
100	1		_aKulkarni, Parag, _eautor
245	1	0	_aReverse hypothesis machine learning : _bpractitioner's perspective _cParag Kulkarni.
264		1	_aCham, Switzerland _bSpringer _c2017.
300			_a1 recurso en línea _bilustraciones
336			_aTexto _btxt _2rdacontent
337			_aelectrónico _bc _2rdamedia
338			_arecurso electrónico _bcr _2rdacarrier
347			_atext file _bPDF _2rda
490	0		_aIntelligent systems reference library _vVolume 128
500			_aSpringerLink _bSpringer Engineering eBooks 2017 English+International
504			_aIncluye referencias bibliográficas e índice
505	0		_aAcknowledgements; Author's Note; Contents; About the Author; Building Foundation: Decoding Knowledge Acquisition; 1 Introduction: Patterns Apart; 1.1 A Naked World of Data Warriors!; 1.2 Introduction-The Blind Data Game; 1.3 Putting Creativity on Weak Legs: Can We Make Present Machines Creative?; 1.4 Learning Using Creative Models; 1.5 Plundered Every Data Point-Data Rich Knowledge Poor Society; 1.6 Computational Creativity and Data Analysis; 1.7 Simple Paradigms and Evaluations: (Machine Learning Compass and Barometer).
505	8		_a1.8 After All Its Time for Knowledge Innovation-Do not just Build Innovate1.9 What Is Knowledge Innovation? (Meta-Knowledge Approach); 1.10 Knowledge Innovation Model Building; 1.11 Creative Intelligence to Collective Knowledge Innovation: (Intelligible Togetherness); 1.12 Do not Dive Deep Unnecessarily: (Your Machine Learning Life Guard in Deep Data Sea); 1.13 Machine Learning and Knowledge Innovation; 1.14 Making Intelligent Agent Intelligent; 1.15 Architecting Intelligence; 1.16 Summary; 2 Understanding Machine Learning Opportunities.
505	8		_a2.1 Understanding Learning Opportunity (Catching Data Signals Right)2.2 Knowledge Innovation Building Blocks of ML and Intelligent Systems; 2.3 Stages in Limited Exploration; 2.4 Mathematical Equations for Classification; 2.5 New Paradigms in This Book; 2.6 iknowlation's IDEA Matrix for Machine Learning Opportunity Evaluation; 2.7 Using IDEA Matrix to Identify ML Opportunity; 2.8 Self-evaluation of Learning; 2.9 Mathematical Model of Learnability; 2.10 Building Machine Learning Models: Your Foundation for Surprising Solutions; 2.11 Opportunity Cycle; 2.12 ML Big Landscape.
505	8		_a2.13 Context-Based Learning-Respect Heterogeneity2.14 Summary; 3 Systemic Machine Learning; 3.1 What Is a System? (Decoding Connectivity); 3.2 What Is Systemic Machine Learning: (Exploiting Togetherness); 3.3 Systemic Machine Learning Model and Algorithm Selection; 3.4 Cognitive Systemic Machine Learning Models; 3.5 Cognitive Interaction Centric Models; 3.6 Meta-Reasoning Centric Models (System of System); 3.6.1 System Study; 3.6.2 Learning with Limited Data; 3.7 Summary; 4 Reinforcement and Deep Reinforcement Machine Learning; 4.1 Introduction; 4.2 Reinforcement Learning; 4.3 Learning Agents.
505	8		_a4.4 Returns and Reward Calculations (Evaluate Your Position and Actions)4.5 Dynamic Systems (Making Best Use of Unpredictability); 4.6 Dynamic Environment and Dynamic System; 4.7 Reinforcement Learning and Exploration; 4.8 Markov Property and Markov Decision Process; 4.9 Value Functions; 4.10 Action and Value; 4.11 Learning an Optimal Policy (Model-Based and Model-Free Methods); 4.12 Uncertainty; 4.13 Adaptive Dynamic Learning (Learning Evolution); 4.14 Temporal Difference (TD) Learning; 4.15 Q Learning; 4.16 Unified View; 4.17 Deep Exploratory Machine Learning; 4.18 Summary.
520	3		_aThis book introduces a paradigm of reverse hypothesis machines (RHM), focusing on knowledge innovation and machine learning. Knowledge- acquisition -based learning is constrained by large volumes of data and is time consuming. Hence Knowledge innovation based learning is the need of time. Since under-learning results in cognitive inabilities and over-learning compromises freedom, there is need for optimal machine learning. All existing learning techniques rely on mapping input and output and establishing mathematical relationships between them. Though methods change the paradigm remains the same--the forward hypothesis machine paradigm, which tries to minimize uncertainty. The RHM, on the other hand, makes use of uncertainty for creative learning. The approach uses limited data to help identify new and surprising solutions. It focuses on improving learnability, unlike traditional approaches, which focus on accuracy. The book is useful as a reference book for machine learning researchers and professionals as well as machine intelligence enthusiasts. It can also used by practitioners to develop new machine learning applications to solve problems that require creativity.
650		7	_aAprendizaje automático _2embne _0(OCoLC)fst01004795 _0 _9166090
856	4	0	_uhttps://go.openathens.net/redirector/universidadeuropea.es?url=http://link.springer.com/10.1007/978-3-319-55312-2 _zAcceso a este recurso digital (usuarios Universidad Europea de Madrid)
988			_aEBOOK, asignarmaterias, EBSPRINGER_2017C
998			_b02/2018 _dz _e- _zSI
999			_c95718 _d95718 _x1