Incremental concept learning for bounded data mining.

DOI10.1006/inco.1998.2784zbMath1045.68572OpenAlexW2002286886MaRDI QIDQ1854293

John Case, Thomas Zeugmann, Steffen Lange, Sanjay Jain

Publication date: 14 January 2003

Published in: Information and Computation (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/2324/3005

zbMATH Keywords

learning machine

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (39)

On the data consumption benefits of accepting increased uncertainty ⋮ Automatic learners with feedback queries ⋮ Results on memory-limited U-shaped learning ⋮ Parsimony hierarchies for inductive inference ⋮ Strongly non-U-shaped language learning results by general techniques ⋮ From learning in the limit to stochastic finite learning ⋮ Learning a subclass of regular patterns in polynomial time ⋮ Learning from Positive Data and Negative Counterexamples: A Survey ⋮ Iterative learning from positive data and counters ⋮ Iterative learning from texts and counterexamples using additional information ⋮ Gold-Style Learning Theory ⋮ Parallelism Increases Iterative Learning Power ⋮ Learning with ordinal-bounded memory from positive data ⋮ Learning recursive functions: A survey ⋮ Learning indexed families of recursive languages from positive data: A survey ⋮ Non-U-shaped vacillatory and team learning ⋮ Some natural conditions on incremental learning ⋮ Teaching randomized learners with feedback ⋮ On the learnability of recursively enumerable languages from good examples ⋮ Synthesizing learners tolerating computable noisy data ⋮ Iterative learning of simple external contextual languages ⋮ Incremental learning with temporary memory ⋮ Learning in the limit with lattice-structured hypothesis spaces ⋮ Topological separations in inductive inference ⋮ Resource restricted computability theoretic learning: Illustrative topics and problems ⋮ U-shaped, iterative, and iterative-with-counter learning ⋮ Parallelism increases iterative learning power ⋮ Automatic Learners with Feedback Queries ⋮ Incremental learning of approximations from positive data ⋮ An average-case optimal one-variable pattern language learner ⋮ Iterative Learning from Texts and Counterexamples Using Additional Information ⋮ Incremental Learning with Ordinal Bounded Example Memory ⋮ Priced Learning ⋮ On learning to coordinate: random bits help, insightful normal forms, and competency isomorphisms ⋮ On the power of incremental learning. ⋮ Learning via finitely many queries ⋮ Variants of iterative learning ⋮ Towards a map for incremental learning in the limit from positive and negative information ⋮ Learning languages in the limit from positive information with finitely many memory changes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Comparison of identification criteria for machine inductive inference
• Inductive inference of monotonic formal systems from positive data
• Polynomial-time inference of arbitrary pattern languages
• Finding patterns common to a set of strings
• Learning elementary formal systems
• Lange and Wiehagen's pattern language learning algorithm: An average-case analysis with respect to its total learning time
• On the role of procrastination in machine learning
• Incremental learning from positive data
• Characterizations of monotonic and dual monotonic language learning
• Theory of Formal Systems. (AM-47)
• A class of prolog programs inferable from positive data
• Inductive inference of formal languages from positive data
• Periodicity in generations of automata
• Toward a mathematical theory of inductive inference
• The Power of Vacillation in Language Learning
• LEARNING RECURSIVE LANGUAGES WITH BOUNDED MIND CHANGES
• Infinitary self-reference in learning theory
• Ignoring data may be the only way to learn efficiently
• Inclusion is undecidable for pattern languages
• Set-driven and rearrangement-independent learning of recursive languages
• A Machine-Independent Theory of the Complexity of Recursive Functions
• Language identification in the limit
• Inductive inference of unbounded unions of pattern languages from positive data

This page was built for publication: Incremental concept learning for bounded data mining.