Computational Learning Theory: Third European Conference, EuroCOLT '97, Jerusalem, Israel, March 17 - 19, 1997, Proceedings, 3. sējumsShai Ben-David Springer Science & Business Media, 1997. gada 3. marts - 330 lappuses This book constitutes the refereed proceedings of the Third European Conference on Computational Learning Theory, EuroCOLT'97, held in Jerusalem, Israel, in March 1997. The book presents 25 revised full papers carefully selected from a total of 36 high-quality submissions. The volume spans the whole spectrum of computational learning theory, with a certain emphasis on mathematical models of machine learning. Among the topics addressed are machine learning, neural nets, statistics, inductive inference, computational complexity, information theory, and theoretical physics. |
Saturs
Sample Compression Learnability and the VapnikChervonenkis Dimension | |
Learning Boxes in High Dimension | 1 |
Learning Monotone Term Decision Lists | 14 |
Learning Matrix Functions over Rings | 25 |
Learning from Incomplete Boundary Queries Using Split Graphs and Hypergraphs | 36 |
Generalization of the PACmodel for Learning with Partial Information | 49 |
Monotonic and DualMonotonic Probabilistic Language Learning of Indexed Families with High Probability | 63 |
Closedness Properties in Team Learning of Recursive Functions | 76 |
Optimal AttributeEfficient Learning of Disjunction Parity and Threshold Functions | 168 |
Learning Pattern Languages Using Queries | 182 |
On Fast and Simple Algorithms for Finding Maximal Subarrays and Applications in Learning Theory | 195 |
A Minimax Lower Bound for Empirical Quantizer Design | 207 |
VapnikChervonenkis Dimension of Recurrent Neural Networks | 220 |
Linear Algebraic Proofs of VCDimension Based Inequalities | 235 |
Numbers with Some Applications to Neural | 248 |
Examples | 257 |
Structural Measures for Games and Process Control in the Branch Learning Model | 91 |
Learning under Persistent Drift | 106 |
Randomized Hypotheses and Minimum Disagreement Hypotheses for Learning with Noise | 116 |
Learning When to Trust Which Experts | 131 |
On Learning Branching Programs and Small Depth Circuits | 147 |
Learning Nearly Monotone Aterm DNF | 159 |
Learning Formulae from Elementary Facts | 269 |
The Influence on Learning | 283 |
Identification | 298 |
Robust Learning with Infinite Additional Information | 313 |
Author Index | 328 |
Citi izdevumi - Skatīt visu
Bieži izmantoti vārdi un frāzes
Angluin approximation assignment binary Boolean functions boxes branching programs classifier competency class complexity Computational Learning Theory Computer Science concept consider constant contains control structures Corollary correct counterexample decision trees defined Definition denote distribution DNF formulae equivalence queries error essential elements experts finite function f Hence hypergraph hypothesis space identified indexed family inductive inference infinite recursive branch input instance space k-term monotone decision labeled learner learning algorithm Lemma linear lower bound Machine Learning membership queries minimal minterm monotone decision lists natural numbers node noise rate optimal oracle ordinal mind change output PAC learning paper pattern languages poly(n polynomial positive example prediction probabilistic problem Proc pseudo-dimension quantizer query sets random recursive functions result sample Section sequence split graph strategies string subset target class target function teams term Turing degree upper bound values VC dimension vector