An MML-based tool for evaluating the complexity of (stochastic) logic theories
Explore this paper's citation graph
Summary
This work presents the first general MML coding scheme for logic programs, which can quantify the bits of information required to code a theory, a set of data or the same data given the theory and illustrates the application of the tool to a variety of non-probabilistic and probabilistic scenarios.
- Type
- preprint
- Published
- 2012-10-22
- Cited by
- 1
- References
- 88
- Access
- Open access
- OpenAlex
- https://openalex.org/W1946701026
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:12876759
Keywords
Computer science, Turing machine, Theoretical computer science, Universal Turing machine, Simplicity
References
- A Computational Definition of 'Consilience’
- The Best Explanation: Criteria for Theory Choice
- General Bayesian networks and asymmetric languages
- Inductive Logic Programming
- Requirements Analysis: From Business Views to Architecture
- Invited review of the book Statistical and Inductive Inference by Minimum Message Length
- Relational Bayesian Networks
- Towards Learning Stochastic Logic Programs from Proof-Banks
- Duce, An Oracle-based Approach to Constructive Induction
- Thesis: Computational measures of information gain and reinforcement in inference processes
- The PITA system: Tabling and answer subsumption for reasoning under uncertainty
- Minimum Message Length and Kolmogorov Complexity
- Aesthetic Constraints on Theory Selection: A Critique of Laudan
- Modeling By Shortest Data Description*
- Foundations of Program Evaluation: Theories of Practice
- Constructive reinforcement learning
- The Independent Choice Logic for Modelling Multiple Agents Under Uncertainty
- Key Concepts in Model Selection: Performance and Generalizability.
- Introduction to WordNet: An On-line Lexical Database
- A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH
Cited by
Related papers
- Complexity–Based Induction
- FIFTH system for general-purpose connectionist computation
- Some aspects of studying an optimization or decision problem in different computational models
- Statistical and logical methods for property checking
- Machine Learning for Data Management: Problems and Solutions
- Applications of finite model theory : optimisation problems, hybrid modal logics and games