Agnostic learning of geometric patterns
From MaRDI portal
Recommendations
- A theoretical and empirical study of a noise-tolerant algorithm to learn geometric patterns
- Noise-tolerant distribution-free learning of general geometric concepts
- A 32-point n=12, d=5 code (Corresp.)
- scientific article; zbMATH DE number 1256730
- scientific article; zbMATH DE number 2095981
- Exact Learning of Discretized Geometric Concepts
- Multiple-instance learning of real-valued geometric patterns
Cites work
- scientific article; zbMATH DE number 3744021 (Why is no real title available?)
- scientific article; zbMATH DE number 67625 (Why is no real title available?)
- scientific article; zbMATH DE number 1559547 (Why is no real title available?)
- A note on learning from multiple-instance examples
- A theoretical and empirical study of a noise-tolerant algorithm to learn geometric patterns
- A theory of the learnable
- Computational limitations on learning from examples
- Decision theoretic generalizations of the PAC model for neural net and other learning applications
- Efficient learning with virtual threshold gates
- Efficient noise-tolerant learning from statistical queries
- Equivalence of models for polynomial learnability
- Exact Learning of Discretized Geometric Concepts
- Learnability and the Vapnik-Chervonenkis dimension
- PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples
- Queries and concept learning
- Solving the multiple instance problem with axis-parallel rectangles.
- Specification and simulation of statistical query algorithms for efficiency and noise tolerance
- The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant
- The weighted majority algorithm
- Toward efficient agnostic learning
- Tracking the best disjunction
Cited in
(5)- Intrinsic complexity of learning geometrical concepts from positive data
- A theoretical and empirical study of a noise-tolerant algorithm to learn geometric patterns
- Improved MCMC sampling methods for estimating weighted sums in Winnow with application to DNF learning
- On learning unions of pattern languages and tree patterns in the mistake bound model.
- On approximating weighted sums with exponentially many terms
This page was built for publication: Agnostic learning of geometric patterns
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5943123)
