Learning figures with the Hausdorff metric by fractals -- towards computable binary classification

DOI10.1007/s10994-012-5301-zzbMath1260.68345OpenAlexW2025650579MaRDI QIDQ1945017

Mahito Sugiyama, Eiju Hirowatari, Hideki Tsuiki, Akihiro Yamamoto

Publication date: 28 March 2013

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-012-5301-z

zbMATH Keywords

discretizationHausdorff metricbinary classificationself-similar settype-2 theory of effectivityGold's learning model

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Fractals (28A80) Hausdorff and packing measures (28A78)

Related Items (1)

Hausdorff dimension, heavy tails, and generalization in neural networks*

Uses Software

• iRRAM
• PRMLT

Cites Work

• Hypothesis spaces for learning
• Towards a mathematical theory of machine discovery from facts
• Elementary formal systems, intrinsic complexity, and procrastination
• Monotonic and non-monotonic inductive inference
• Learning recursive functions: A survey
• Learning indexed families of recursive languages from positive data: A survey
• Partial observability and learnability
• Some natural properties of strong-identification in inductive inference
• Learning with restricted focus of attention
• On the inductive inference of recursive real-valued functions
• Computability on subsets of Euclidean space. I: Closed and compact subsets
• PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples
• Learning from examples with unspecified attribute values.
• Computability on subsets of metric spaces.
• Extended admissibility.
• A general lower bound on the number of examples needed for learning
• Refutable language learning with a neighbor system.
• Refuting learning revisited.
• Characterizations of monotonic and dual monotonic language learning
• Geometric measure theory.
• Learning to reason with a restricted view
• Uncountable automatic classes and learning
• Sigma^0_alpha - Admissible Representations (Extended Abstract)
• Learnability and the Vapnik-Chervonenkis dimension
• Prediction of Recursive Real-Valued Functions from Finite Examples
• A theory of the learnable
• Inductive inference of formal languages from positive data
• Inference of Reversible Languages
• Toward a mathematical theory of inductive inference
• Characterization of language learning front informant under various monotonicity constraints
• Learning Figures with the Hausdorff Metric by Fractals
• Limiting recursion
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Language identification in the limit
• On Computable Numbers, with an Application to the Entscheidungsproblem
• A comparison of identification criteria for inductive inference of recursive real-valued functions
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Learning figures with the Hausdorff metric by fractals -- towards computable binary classification