Descripción del título
Computational Learning Theo...
This volume presents the proceedings of the Second European Conference on Computational Learning Theory (EuroCOLT '95), held in Barcelona, Spain in March 1995. The book contains full versions of the 28 papers accepted for presentation at the conference as well as three invited papers. All relevant topics in fundamental studies of computational aspects of artificial and natural learning systems and machine learning are covered; in particular artificial and biological neural networks, genetic and evolutionary algorithms, robotics, pattern recognition, inductive logic programming, decision theory, Bayesian/MDL estimation, statistical physics, and cryptography are addressed
Monografía
monografia Rebiun21555153 https://catalogo.rebiun.org/rebiun/record/Rebiun21555153 m o d cr nn|008mamaa 121227s1995 gw o 000 0 eng 827359865 851762701 990658549 993767050 1005771760 1036772209 1044504523 9783540491958 electronic bk.) 3540491953 electronic bk.) 3540491953 9783540591191 10.1007/3-540-59119-2 doi UPVA 996968401803706 Nz eng pn UV0 OCLCO GW5XE OCLCA ITD OCLCF KIJ OCLCQ VT2 OCLCQ UAB ESU OCLCQ TFW AU@ OCLCA UYQ bicssc TJFM1 bicssc COM004000 bisacsh Computational Learning Theory Second European Conference, EuroCOLT '95 Barcelona, Spain, March 13-15, 1995 Proceedings edited by Paul Vitányi Berlin, Heidelberg Springer Berlin Heidelberg 1995 Berlin, Heidelberg Berlin, Heidelberg Springer Berlin Heidelberg 1 online resource (XVII, 415 pages) 1 online resource (XVII, 415 pages) Text txt rdacontent computer c rdamedia online resource cr rdacarrier Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence 0302-9743 904 The discovery of algorithmic probability: A guide for the programming of true creativity -- A desicion-theoretic generalization of on-line learning and an application to boosting -- Online learning versus offline learning -- Learning distributions by their density levels A paradigm for learning without a teacher -- Tight worst-case loss bounds for predicting with expert advice -- On-line maximum likelihood prediction with respect to general loss functions -- The power of procrastination in inductive inference: How it depends on used ordinal notations -- Learnability of Kolmogorov-easy circuit expressions via queries -- Trading monotonicity demands versus mind changes -- Learning recursive functions from approximations -- On the intrinsic complexity of learning -- The structure of intrinsic complexity of learning -- Kolmogorov numberings and minimal identification -- Stochastic complexity in learning -- Function learning from interpolation (extended abstract) -- Approximation and learning of convex superpositions -- Minimum description length estimators under the optimal coding scheme -- MDL learning of unions of simple pattern languages from positive examples -- A note on the use of probabilities by mechanical learners -- Characterizing rational versus exponential learning curves -- Is pocket algorithm optimal? -- Some theorems concerning the free energy of (Un) constrained stochastic Hopfield neural networks -- A space-bounded learning algorithm for axis-parallel rectangles -- Learning decision lists and trees with equivalence-queries -- Bounding VC-dimension for neural networks: Progress and prospects -- Average case analysis of a learning algorithm for ?-DNF expressions -- Learning by extended statistical queries and its relation to PAC learning -- Typed pattern languages and their learnability -- Learning behaviors of automata from shortest counterexamples -- Learning of regular expressions by pattern matching -- The query complexity of learning some subclasses of context-free grammars This volume presents the proceedings of the Second European Conference on Computational Learning Theory (EuroCOLT '95), held in Barcelona, Spain in March 1995. The book contains full versions of the 28 papers accepted for presentation at the conference as well as three invited papers. All relevant topics in fundamental studies of computational aspects of artificial and natural learning systems and machine learning are covered; in particular artificial and biological neural networks, genetic and evolutionary algorithms, robotics, pattern recognition, inductive logic programming, decision theory, Bayesian/MDL estimation, statistical physics, and cryptography are addressed Computer science Computer software Artificial intelligence Artificial intelligence. Computer science. Computer software. Computer Science. Engineering & Applied Sciences. Electronic books Electronic books. Vitányi, Paul Print version 9783540591191 Lecture notes in computer science. Lecture notes in artificial intelligence 904. 0302-9743