Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
From MaRDI portal
Publication:1106669
DOI10.1016/0004-3702(88)90002-1zbMath0651.68104OpenAlexW1994022788MaRDI QIDQ1106669
Publication date: 1988
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0004-3702(88)90002-1
Related Items
Theory refinement combining analytical and empirical methods, Iterative versionspaces, The minimum feature set problem, DNA sequencing and string learning, Autonomous theory building systems, Shifting vocabulary bias in speedup learning, A sufficient condition for polynomial distribution-dependent learnability, An approach to guided learning of Boolean functions, The gap between abstract and concrete results in machine learning, PALO: a probabilistic hill-climbing algorithm, Partial Occam's Razor and its applications, System design and evaluation using discrete event simulation with AI, Noise modelling and evaluating learning from examples, Inductive constraint logic, Advanced discretization techniques for hyperelastic physics-augmented neural networks, Solving the multiple instance problem with axis-parallel rectangles., Parameterized Learnability of k-Juntas and Related Problems, AN ALTERNATIVE METHOD OF CONCEPT LEARNING, Learning the set covering machine by bound minimization and margin-sparsity trade-off, Learning nested concept classes with limited storage, Inductive logic programming, Embedding decision-analytic control in a learning architecture, Principles of metareasoning, Constraint acquisition, Learning decision trees with taxonomy of propositionalized attributes, Decision theoretic generalizations of the PAC model for neural net and other learning applications, Reasoning about model accuracy, Bounding sample size with the Vapnik-Chervonenkis dimension, Hyperrelations in version space, Precise induction from statistical data, Improved learning of \(k\)-parities, On the fusion of threshold classifiers for categorization and dimensionality reduction, Computational sample complexity and attribute-efficient learning, Robust logics, Sharpening Occam's razor, Prediction-preserving reducibility, Specification and simulation of statistical query algorithms for efficiency and noise tolerance, Learning decision trees from random examples, A general lower bound on the number of examples needed for learning, Scaling, machine learning, and genetic neural nets, Parameterized learnability of juntas, Finite electro-elasticity with physics-augmented neural networks, A reduction algorithm meeting users' requirements., Combinatorics and connectionism, A result of Vapnik with applications, A computational study on the performance of artificial neural networks under changing structural design and data distribution, The complexity of theory revision, Version spaces and the consistency problem
Cites Work
- Unnamed Item
- Unnamed Item
- An analytical comparison of some rule-learning programs
- \(\epsilon\)-nets and simplex range queries
- Occam's razor
- Modeling by shortest data description
- Some special Vapnik-Chervonenkis classes
- Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
- Approximation algorithms for combinatorial problems
- Learning decision trees from random examples
- A general lower bound on the number of examples needed for learning
- Queries and concept learning
- Learnability and the Vapnik-Chervonenkis dimension
- A theory of the learnable
- Computational limitations on learning from examples
- A Greedy Heuristic for the Set-Covering Problem
- ON THE CONNECTION BETWEEN THE COMPLEXITY AND CREDIBILITY OF INFERRED MODELS
- On Knapsacks, Partitions, and a New Dynamic Programming Technique for Trees
- Learning structural shape descriptions from examples
- Enumeration of Seven-Argument Threshold Functions
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
