On the impact of forgetting on learning machines

DOI10.1145/227683.227685zbMath0891.68088OpenAlexW2011659139WikidataQ127705398 ScholiaQ127705398MaRDI QIDQ4369894

Carl H. Smith, E. B. Kinber, Rūsiņš Freivalds

Publication date: 28 January 1998

Published in: Journal of the ACM (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/227683.227685

zbMATH Keywords

inductive inferencememory limited learningKolomogorov complexity

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30)

Related Items (16)

On the data consumption benefits of accepting increased uncertainty ⋮ Automatic learners with feedback queries ⋮ Results on memory-limited U-shaped learning ⋮ Iterative learning from positive data and counters ⋮ Quantum inductive inference by finite automata ⋮ Learning and extending sublanguages ⋮ Automatic learning of subclasses of pattern languages ⋮ Learnability of automatic classes ⋮ Automatic learning from positive data and negative counterexamples ⋮ The functions of finite support: a canonical learning problem ⋮ Learners based on transducers ⋮ Automatic Learners with Feedback Queries ⋮ An average-case optimal one-variable pattern language learner ⋮ Priced Learning ⋮ On learning to coordinate: random bits help, insightful normal forms, and competency isomorphisms ⋮ Learning via finitely many queries

This page was built for publication: On the impact of forgetting on learning machines