Ignoring data may be the only way to learn efficiently

DOI10.1080/09528139408953785zbMATH Open0803.68109OpenAlexW2013541926MaRDI QIDQ4290134FDOQ4290134

Authors: Rolf Wiehagen, Thomas Zeugmann 

Publication date: 3 May 1994

Published in: Journal of Experimental & Theoretical Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/09528139408953785

Recommendations

• Learning from a consistently ignorant teacher
• Knowing what doesn't matter: exploiting the omission of irrelevant data
• Learning by erasing
• Occam's razor
• Learning in the presence of finitely or infinitely many irrelevant attributes

zbMATH Keywords

learning algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Title not available (Why is that?)
• A formal theory of inductive inference. Part I
• Toward a mathematical theory of inductive inference
• Title not available (Why is that?)
• Language identification in the limit
• Finding patterns common to a set of strings
• A Machine-Independent Theory of the Complexity of Recursive Functions
• Polynomial-time inference of arbitrary pattern languages
• Limiting recursion
• Saving the phenomena: Requirements that inductive inference machines not contradict known data
• Nonmonotonic and inductive logic. 1st international workshop, Karlsruhe, Germany, December 4--7, 1990. Proceedings

Cited In (25)

• An average-case optimal one-variable pattern language learner
• Set-driven and rearrangement-independent learning of recursive languages
• On the interplay between inductive inference of recursive functions, complexity theory and recursive numberings
• Learning languages from positive data and a limited number of short counterexamples
• Co-learning of recursive languages from positive data
• Inferring descriptive generalisations of formal languages
• Learning indexed families of recursive languages from positive data: A survey
• Monotonic and dual monotonic language learning
• Learning efficiency of very simple grammars from positive data
• On families of categorial grammars of bounded value, their learnability and related complexity questions
• Developments from enquiries into the learnability of the pattern languages from positive data
• Learning one-variable pattern languages very efficiently on average, in parallel, and by asking queries
• From learning in the limit to stochastic finite learning
• Consistent and coherent learning with \(\delta \)-delay
• A non-learnable class of E-pattern languages
• Discontinuities in pattern inference
• Revisiting Shinohara's algorithm for computing descriptive patterns
• On learning unions of pattern languages and tree patterns in the mistake bound model.
• Robust learning -- rich and poor
• Inductive inference of approximations for recursive concepts
• Learning recursive functions: A survey
• Non-U-shaped vacillatory and team learning
• Quantum inductive inference by finite automata
• Learning Efficiency of Very Simple Grammars from Positive Data
• Incremental concept learning for bounded data mining.

This page was built for publication: Ignoring data may be the only way to learn efficiently

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4290134)