Comparison of identification criteria for machine inductive inference

DOI10.1016/0304-3975(83)90061-0zbMATH Open0524.03025OpenAlexW2018722248MaRDI QIDQ585192FDOQ585192

Authors: Jianyong Qiao, Sumit K. Garg 

Publication date: 1983

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0304-3975(83)90061-0

zbMATH Keywords

identificationinductive inferencephilosophy of scienceanomalies in programsinherent relative computational complexityrecursive function theorytradeoff results

Mathematics Subject Classification ID

Complexity of computation (including implicit computational complexity) (03D15) Recursive functions and relations, subrecursive hierarchies (03D20) Turing machines and related notions (03D10)

Cites Work

• Title not available (Why is that?)
• Some natural properties of strong-identification in inductive inference
• Title not available (Why is that?)
• Toward a mathematical theory of inductive inference
• Title not available (Why is that?)
• Language identification in the limit
• Three theorems on recursive enumeration. I. Decomposition. II. Maximal set. III. Enumeration without duplication
• Classes of computable functions defined by bounds on computation
• A Machine-Independent Theory of the Complexity of Recursive Functions
• Title not available (Why is that?)
• The Power of Pluralism for Automatic Program Synthesis
• Periodicity in generations of automata
• Title not available (Why is that?)
• Some decidability results on grammatical inference and complexity
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Mechanism, mentalism, and metamathematics. An essay on finitism
• Research in the theory of inductive inference by GDR mathematicians - A survey
• Gödel numberings of partial recursive functions
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Anomaly hierarchies of mechanized inductive inference
• On the size of machines
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (only showing first 100 items - show all)

• Learning and classifying
• Learning in the presence of partial explanations
• The complexity of finding SUBSEQ\((A)\)
• Machine learning of higher-order programs
• Automata techniques for query inference machines
• The synthesis of language learners.
• Recursion theoretic models of learning: Some results and intuitions
• Hypothesis spaces for learning
• Learning via queries in [+, <]
• Computability-theoretic learning complexity
• Learning pattern languages over groups
• On the learnability of recursively enumerable languages from good examples
• Parsimony hierarchies for inductive inference
• Learning languages from positive data and negative counterexamples
• Learning algebraic structures from text
• An approach to intrinsic complexity of uniform learning
• Infinitary self-reference in learning theory
• The independence of control structures in abstract programming systems
• Synthesizing inductive expertise
• Resource restricted computability theoretic learning: Illustrative topics and problems
• Learning all subfunctions of a function
• Classes with easily learnable subclasses
• A note on batch and incremental learnability
• Learning from Positive Data and Negative Counterexamples: A Survey
• On the intrinsic complexity of learning recursive functions
• Robust learning is rich
• Learning by switching type of information.
• Probability and plurality for aggregations of learning machines
• Confident and consistent partial learning of recursive functions
• On the power of inductive inference from good examples
• Learning via finitely many queries
• Optimal language learning from positive data
• Robust learning aided by context
• Avoiding coding tricks by hyperrobust learning
• Ordinal mind change complexity of language identification
• Title not available (Why is that?)
• Training sequences
• Iterative learning from positive data and negative counterexamples
• Enlarging learnable classes
• Strongly non-U-shaped language learning results by general techniques
• Robust learning -- rich and poor
• Learning via queries and oracles
• Dynamic Modeling in Inductive Inference
• Learning multiple languages in groups
• On the classification of recursive languages
• Inductive reasoning and Kolmogorov complexity
• Generality's price: Inescapable deficiencies in machine-learned programs
• Closedness properties in ex-identification
• Learning families of closed sets in matroids
• Learning recursive functions: A survey
• Non-U-shaped vacillatory and team learning
• Saving the phenomena: Requirements that inductive inference machines not contradict known data
• On the relative sizes of learnable sets
• Predictive learning models for concept drift
• Probabilistic language learning under monotonicity constraints
• Separation of uniform learning classes.
• Maximal machine learnable classes
• Extremes in the degrees of inferability
• Learning languages and functions by erasing
• Language learning from texts: Degrees of intrinsic complexity and their characterizations
• On an open problem in classification of languages
• Learning and extending sublanguages
• On the inference of approximate programs
• One-sided error probabilistic inductive inference and reliable frequency identification
• Generalization versus classification
• Anomalous learning helps succinctness
• Realism, rhetoric, and reliability
• Robust separations in inductive inference
• Mind change speed-up for learning languages from positive data
• Learning in the presence of inaccurate information
• Incremental concept learning for bounded data mining.
• Inferring answers to queries
• Generalized notions of mind change complexity
• On a question about learning nearly minimal programs
• Training digraphs
• Towards a mathematical theory of machine discovery from facts
• Identification of function distinguishable languages.
• On the interplay between inductive inference of recursive functions, complexity theory and recursive numberings
• Kolmogorov numberings and minimal identification
• Costs of general purpose learning
• Prediction of Recursive Real-Valued Functions from Finite Examples
• Learning languages from positive data and a limited number of short counterexamples
• Learning languages from positive data and a finite number of queries
• Aggregating inductive expertise on partial recursive functions
• Variations on U-shaped learning
• Intrinsic complexity of learning geometrical concepts from positive data
• Trees and learning
• Learning-theoretic perspectives of acceptable numberings
• On unstable and unoptimal prediction
• On the power of recursive optimizers
• Algorithmic identification of probabilities is hard
• Causal learning with Occam's razor
• Theory choice, theory change, and inductive truth-conduciveness
• Learnability and positive equivalence relations
• Counting extensional differences in BC-learning
• Learning how to separate.
• Increasing the power of uniform inductive learners
• Gold-style learning theory. A selection of highlights since Gold
• Measure, category and learning theory
• Spatial/kinematic domain and lattice computers

This page was built for publication: Comparison of identification criteria for machine inductive inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q585192)