000			03965nam a22005055i 4500
001			978-0-387-25061-8
003			DE-He213
005			20170628033240.0
007			cr nn 008mamaa
008			100301s2005 xxu| s |||| 0|eng d
020			_a9780387250618 _9978-0-387-25061-8
024	7		_a10.1007/b106715 _2doi
050		4	_aQ334-342
050		4	_aTJ210.2-211.495
072		7	_aUYQ _2bicssc
072		7	_aTJFM1 _2bicssc
072		7	_aCOM004000 _2bisacsh
082	0	4	_a006.3 _223
100	1		_aVovk, Vladimir. _eauthor.
245	1	0	_aAlgorithmic Learning in a Random World _h[electronic resource] / _cby Vladimir Vovk, Alexander Gammerman, Glenn Shafer.
264		1	_aBoston, MA : _bSpringer US, _c2005.
300			_aXVI, 324 p. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
347			_atext file _bPDF _2rda
505	0		_aConformal prediction -- Classification with conformal predictors -- Modifications of conformal predictors -- Probabilistic prediction I: impossibility results -- Probabilistic prediction II: Venn predictors -- Beyond exchangeability -- On-line compression modeling I: conformal prediction -- On-line compression modeling II: Venn prediction -- Perspectives and contrasts.
520			_aConformal prediction is a valuable new method of machine learning. Conformal predictors are among the most accurate methods of machine learning, and unlike other state-of-the-art methods, they provide information about their own accuracy and reliability. This new monograph integrates mathematical theory and revealing experimental work. It demonstrates mathematically the validity of the reliability claimed by conformal predictors when they are applied to independent and identically distributed data, and it confirms experimentally that the accuracy is sufficient for many practical problems. Later chapters generalize these results to models called repetitive structures, which originate in the algorithmic theory of randomness and statistical physics. The approach is flexible enough to incorporate most existing methods of machine learning, including newer methods such as boosting and support vector machines and older methods such as nearest neighbors and the bootstrap. Topics and Features: * Describes how conformal predictors yield accurate and reliable predictions, complemented with quantitative measures of their accuracy and reliability * Handles both classification and regression problems * Explains how to apply the new algorithms to real-world data sets * Demonstrates the infeasibility of some standard prediction tasks * Explains connections with Kolmogorov’s algorithmic randomness, recent work in machine learning, and older work in statistics * Develops new methods of probability forecasting and shows how to use them for prediction in causal networks Researchers in computer science, statistics, and artificial intelligence will find the book an authoritative and rigorous treatment of some of the most promising new developments in machine learning. Practitioners and students in all areas of research that use quantitative prediction or machine learning will learn about important new methods.
650		0	_aComputer science.
650		0	_aData structures (Computer science).
650		0	_aArtificial intelligence.
650		0	_aMathematical statistics.
650	1	4	_aComputer Science.
650	2	4	_aArtificial Intelligence (incl. Robotics).
650	2	4	_aStatistics and Computing/Statistics Programs.
650	2	4	_aData Structures, Cryptology and Information Theory.
700	1		_aGammerman, Alexander. _eauthor.
700	1		_aShafer, Glenn. _eauthor.
710	2		_aSpringerLink (Online service)
773	0		_tSpringer eBooks
776	0	8	_iPrinted edition: _z9780387001524
856	4	0	_uhttp://dx.doi.org/10.1007/b106715
912			_aZDB-2-SCS
999			_c14314 _d14314