000 06375nam a22006375i 4500
001 978-3-540-30215-5
003 DE-He213
005 20240423132529.0
007 cr nn 008mamaa
008 121227s2004 gw | s |||| 0|eng d
020 _a9783540302155
_9978-3-540-30215-5
024 7 _a10.1007/b100989
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
245 1 0 _aAlgorithmic Learning Theory
_h[electronic resource] :
_b15th International Conference, ALT 2004, Padova, Italy, October 2-5, 2004. Proceedings /
_cedited by Shai Ben David, John Case, Akira Maruoka.
250 _a1st ed. 2004.
264 1 _aBerlin, Heidelberg :
_bSpringer Berlin Heidelberg :
_bImprint: Springer,
_c2004.
300 _aXIV, 514 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aLecture Notes in Artificial Intelligence,
_x2945-9141 ;
_v3244
505 0 _aInvited Papers -- String Pattern Discovery -- Applications of Regularized Least Squares to Classification Problems -- Probabilistic Inductive Logic Programming -- Hidden Markov Modelling Techniques for Haplotype Analysis -- Learning, Logic, and Probability: A Unified View -- Regular Contributions -- Learning Languages from Positive Data and Negative Counterexamples -- Inductive Inference of Term Rewriting Systems from Positive Data -- On the Data Consumption Benefits of Accepting Increased Uncertainty -- Comparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space -- Learning r-of-k Functions by Boosting -- Boosting Based on Divide and Merge -- Learning Boolean Functions in AC 0 on Attribute and Classification Noise -- Decision Trees: More Theoretical Justification for Practical Algorithms -- Application of Classical Nonparametric Predictors to Learning Conditionally I.I.D. Data -- Complexity of Pattern Classes and Lipschitz Property -- On Kernels, Margins, and Low-Dimensional Mappings -- Estimation of the Data Region Using Extreme-Value Distributions -- Maximum Entropy Principle in Non-ordered Setting -- Universal Convergence of Semimeasures on Individual Random Sequences -- A Criterion for the Existence of Predictive Complexity for Binary Games -- Full Information Game with Gains and Losses -- Prediction with Expert Advice by Following the Perturbed Leader for General Weights -- On the Convergence Speed of MDL Predictions for Bernoulli Sequences -- Relative Loss Bounds and Polynomial-Time Predictions for the k-lms-net Algorithm -- On the Complexity of Working Set Selection -- Convergence of a Generalized Gradient Selection Approach for the Decomposition Method -- Newton Diagram and Stochastic Complexity in Mixture of Binomial Distributions -- Learnability of Relatively Quantified Generalized Formulas -- Learning Languages Generated by Elementary Formal Systems and Its Application to SH Languages -- New Revision Algorithms -- The Subsumption Lattice and Query Learning -- Learning of Ordered Tree Languages with Height-Bounded Variables Using Queries -- Learning Tree Languages from Positive Examples and Membership Queries -- Learning Content Sequencing in an Educational Environment According to Student Needs -- Tutorial Papers -- Statistical Learning in Digital Wireless Communications -- A BP-Based Algorithm for Performing Bayesian Inference in Large Perceptron-Type Networks -- Approximate Inference in Probabilistic Models.
520 _aAlgorithmic learning theory is mathematics about computer programs which learn from experience. This involves considerable interaction between various mathematical disciplines including theory of computation, statistics, and c- binatorics. There is also considerable interaction with the practical, empirical ?elds of machine and statistical learning in which a principal aim is to predict, from past data about phenomena, useful features of future data from the same phenomena. The papers in this volume cover a broad range of topics of current research in the ?eld of algorithmic learning theory. We have divided the 29 technical, contributed papers in this volume into eight categories (corresponding to eight sessions) re?ecting this broad range. The categories featured are Inductive Inf- ence, Approximate Optimization Algorithms, Online Sequence Prediction, S- tistical Analysis of Unlabeled Data, PAC Learning & Boosting, Statistical - pervisedLearning,LogicBasedLearning,andQuery&ReinforcementLearning. Below we give a brief overview of the ?eld, placing each of these topics in the general context of the ?eld. Formal models of automated learning re?ect various facets of the wide range of activities that can be viewed as learning. A ?rst dichotomy is between viewing learning as an inde?nite process and viewing it as a ?nite activity with a de?ned termination. Inductive Inference models focus on inde?nite learning processes, requiring only eventual success of the learner to converge to a satisfactory conclusion.
650 0 _aArtificial intelligence.
650 0 _aComputer science.
650 0 _aAlgorithms.
650 0 _aMachine theory.
650 0 _aNatural language processing (Computer science).
650 1 4 _aArtificial Intelligence.
650 2 4 _aTheory of Computation.
650 2 4 _aAlgorithms.
650 2 4 _aFormal Languages and Automata Theory.
650 2 4 _aNatural Language Processing (NLP).
700 1 _aBen David, Shai.
_eeditor.
_4edt
_4http://id.loc.gov/vocabulary/relators/edt
700 1 _aCase, John.
_eeditor.
_4edt
_4http://id.loc.gov/vocabulary/relators/edt
700 1 _aMaruoka, Akira.
_eeditor.
_4edt
_4http://id.loc.gov/vocabulary/relators/edt
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783540233565
776 0 8 _iPrinted edition:
_z9783662205204
830 0 _aLecture Notes in Artificial Intelligence,
_x2945-9141 ;
_v3244
856 4 0 _uhttps://doi.org/10.1007/b100989
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
912 _aZDB-2-LNC
912 _aZDB-2-BAE
942 _cSPRINGER
999 _c188775
_d188775