PALO: a probabilistic hill-climbing algorithm
From MaRDI portal
Publication:2171267
DOI10.1016/0004-3702(95)00040-2zbMath1506.68093WikidataQ127642480 ScholiaQ127642480MaRDI QIDQ2171267
Publication date: 23 September 2022
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0004-3702(95)00040-2
computational learning theory; theory revision; knowledge compilation; hill-climbing; utility problem; prioritized default theories; speed-up learning
68T05: Learning and adaptive systems in artificial intelligence
68T30: Knowledge representation
68T20: Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)
Related Items
On the relations between intelligent backtracking and failure-driven explanation-based learning in constraint satisfaction and planning, Improved particle swarm optimization and neighborhood field optimization by introducing the re-sampling step of particle filter, Sequential sampling techniques for algorithmic learning theory
Uses Software
Cites Work
- Optimization by Simulated Annealing
- Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
- Controlling backward inference
- Default reasoning in semantic networks: A formalization of recognition and inheritance
- Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
- Finding optimal derivation strategies in redundant knowledge bases
- Decision theoretic generalizations of the PAC model for neural net and other learning applications
- Optimal problem-solving search: All-or-none solutions
- Theory refinement combining analytical and empirical methods
- Polynomial-time inference of all valid implications for Horn and related formulae
- Probably approximately optimal satisficing strategies
- A theory of the learnable
- Linear-time algorithms for testing the satisfiability of propositional horn formulae
- Probability Inequalities for Sums of Bounded Random Variables
- The complexity of theorem-proving procedures
- A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
- 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