Probability and plurality for aggregations of learning machines
From MaRDI portal
(Redirected from Publication:1104113)
A new notion of probabilistic team inductive inference is introduced and compared with both probabilistic inference and team inference. In many cases, but not all, probabilism can be traded for pluralism, and vice versa. Necessary and sufficient conditions are given describing when a team of deterministic or probabilistic learning machines can be coalesced into a single learning machine. A subtle difference between probabilism and pluralism is revealed.
Recommendations
Cites work
- A theory of the learnable
- Aggregating inductive expertise
- Comparison of identification criteria for machine inductive inference
- scientific article; zbMATH DE number 3655912 (Why is no real title available?)
- scientific article; zbMATH DE number 43947 (Why is no real title available?)
- scientific article; zbMATH DE number 3485660 (Why is no real title available?)
- scientific article; zbMATH DE number 3531360 (Why is no real title available?)
- scientific article; zbMATH DE number 3586480 (Why is no real title available?)
- scientific article; zbMATH DE number 3588020 (Why is no real title available?)
- Language identification in the limit
- On the error correcting power of pluralism in BC-type inductive inference
- On the power of probabilistic strategies in inductive inference
- Some decidability results on grammatical inference and complexity
- The Power of Pluralism for Automatic Program Synthesis
- Toward a mathematical theory of inductive inference
Cited in
(43)- On the relative sizes of learnable sets
- Aggregating inductive expertise on partial recursive functions
- Investigations on measure-one identification of classes of languages
- Extremes in the degrees of inferability
- On aggregating teams of learning machines
- Probabilistic language learning under monotonicity constraints
- Avoiding coding tricks by hyperrobust learning
- On duality in learning and the selection of learning teams
- Trade-off among parameters affecting inductive inference
- The synthesis of language learners.
- PAC learning of probability distributions over a discrete domain.
- Trees and learning
- Recursion theoretic models of learning: Some results and intuitions
- Probability pooling for dependent agents in collective learning
- Fast learning rates in statistical inference through aggregation
- On learning to coordinate: random bits help, insightful normal forms, and competency isomorphisms
- Learning from streams
- Aggregating inductive expertise
- scientific article; zbMATH DE number 4031026 (Why is no real title available?)
- scientific article; zbMATH DE number 4058897 (Why is no real title available?)
- Learning via queries in [+, <]
- scientific article; zbMATH DE number 149519 (Why is no real title available?)
- scientific article; zbMATH DE number 177811 (Why is no real title available?)
- The power of probabilism in Popperian FINite learning
- scientific article; zbMATH DE number 605140 (Why is no real title available?)
- Measure, category and learning theory
- Memory limited inductive inference machines
- Probabilistic and pluralistic learners with mind changes
- scientific article; zbMATH DE number 7307484 (Why is no real title available?)
- A learning algorithm for source aggregation
- scientific article; zbMATH DE number 2217750 (Why is no real title available?)
- Hierarchies of probabilistic and team FIN-learning
- Probabilistic inductive inference: A survey
- Robust learning is rich
- Closedness properties in ex-identification
- Simulating teams with many conjectures
- Input-dependence in function-learning
- On the inference of approximate programs
- Training sequences
- Quantum inductive inference by finite automata
- Absolute versus probabilistic classification in a logical setting
- Probabilistic and team PFIN-type learning: General properties
- Taming teams with mind changes
This page was built for publication: Probability and plurality for aggregations of learning machines
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1104113)
