Probably Approximate Learning of Sets and Functions
From MaRDI portal
DOI10.1137/0220021zbMATH Open0722.68093OpenAlexW2061729190MaRDI QIDQ3210201FDOQ3210201
Authors: B. K. Natarajan 
Publication date: 1991
Published in: SIAM Journal on Computing (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/0220021
Recommendations
- Results on learnability and the Vapnik-Chervonenkis dimension
- Learnability and the Vapnik-Chervonenkis dimension
- Probably Approximate Learning over Classes of Distributions
- Learnability with respect to fixed distributions
- Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
Cited In (43)
- A sufficient condition for polynomial distribution-dependent learnability
- Title not available (Why is that?)
- Implementing Valiant's learnability theory using random sets.
- Title not available (Why is that?)
- The learnability of voting rules
- Top-down decision tree learning as information based boosting
- Decision lists over regular patterns.
- Teaching randomized learners with feedback
- Exact VC-dimension of Boolean monomials
- An introduction to some statistical aspects of PAC learning theory
- PAC learning under helpful distributions
- First-order \(jk\)-clausal theories are PAC-learnable
- Learning faster than promised by the Vapnik-Chervonenkis dimension
- Embeddings and the trace of finite sets
- Multi-class pattern classification using neural networks
- Results on learnability and the Vapnik-Chervonenkis dimension
- Learning nested differences in the presence of malicious noise
- Learning reliably and with one-sided error
- Apple tasting.
- Monotone term decision lists
- Witness sets for families of binary vectors
- Fusion methods for multiple sensor systems with unknown error densities
- Learning dynamical systems in a stationary environment
- Probably Approximate Learning over Classes of Distributions
- Sparse approximate multiquadric interpolation
- Learning distributions by their density levels: A paradigm for learning without a teacher
- Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
- Learnability and the Vapnik-Chervonenkis dimension
- Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
- Learning figures with the Hausdorff metric by fractals -- towards computable binary classification
- Measuring teachability using variants of the teaching dimension
- On the relative sizes of learnable sets
- Learning Theory and Descriptive Set Theory
- Algorithmic Learning Theory
- On the complexity of learning from drifting distributions
- A framework for incremental learning of logic programs
- Valid Generalisation from Approximate Interpolation
- Learning logic programs with structured background knowledge
- Learning with prior information
- Advanced elementary formal systems.
- Theory of Classification: a Survey of Some Recent Advances
- Complexity of computing Vapnik-Chervonenkis dimension and some generalized dimensions
- Neural networks with quadratic VC dimension
This page was built for publication: Probably Approximate Learning of Sets and Functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3210201)
