Klaus P. Jantke / Takeshi Shinohara / Thomas Zeugmann (eds.)

Algorithmic Learning Theory

6th International Workshop, ALT '95, Fukuoka, Japan, October 18 - 20, 1995. Proceedings
Mitarbeit:Jantke, Klaus P.; Shinohara, Takeshi; Zeugmann, Thomas

• Broschiertes Buch

Produktbeschreibung

This book constitutes the refereed proceedings of the 6th International Workshop on Algorithmic Learning Theory, ALT '95, held in Fukuoka, Japan, in October 1995.
The book contains 21 revised full papers selected from 46 submissions together with three invited contributions. It covers all current areas related to algorithmic learning theory, in particular the theory of machine learning, design and analysis of learning algorithms, computational logic aspects, inductive inference, learning via queries, artificial and biologicial neural network learning, pattern recognition, learning by analogy, statistical learning, inductive logic programming, robot learning, and gene analysis.

---

Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.

Produktdetails

• Lecture Notes in Computer Science 997
• Verlag: Springer / Springer Berlin Heidelberg / Springer, Berlin
• Artikelnr. des Verlages: 978-3-540-60454-9
• 1995.
• Seitenzahl: 344
• Erscheinungstermin: 5. Oktober 1995
• Englisch
• Abmessung: 235mm x 155mm x 19mm
• Gewicht: 451g
• ISBN-13: 9783540604549
• ISBN-10: 3540604545
• Artikelnr.: 09234322

Inhaltsangabe

Grammatical inference: An old and new paradigm.- Efficient learning of real time one-counter automata.- Learning strongly deterministic even linear languages from positive examples.- Language learning from membership queries and characteristic examples.- Learning unions of tree patterns using queries.- Inductive constraint logic.- Incremental learning of logic programs.- Learning orthogonal F-Horn formulas.- Learning nested differences in the presence of malicious noise.- Learning sparse linear combinations of basis functions over a finite domain.- Inferring a DNA sequence from erroneous copies (abstract).- Machine induction without revolutionary paradigm shifts.- Probabilistic language learning under monotonicity constraints.- Noisy inference and oracles.- Simulating teams with many conjectures.- Complexity of network training for classes of Neural Networks.- Learning ordered binary decision diagrams.- Simple PAC learning of simple decision lists.- The complexity of learning minor closed graph classes.- Technical and scientific issues of KDD (or: Is KDD a science?).- Analogical logic program synthesis algorithm that can refute inappropriate similarities.- Reflecting and self-confident inductive inference machines.- On approximately identifying concept classes in the limit.- Application of kolmogorov complexity to inductive inference with limited memory.