Search results for "recursive function"

showing 10 items of 26 documents

On the inductive inference of recursive real-valued functions

1999

AbstractWe combine traditional studies of inductive inference and classical continuous mathematics to produce a study of learning real-valued functions. We consider two possible ways to model the learning by example of functions with domain and range the real numbers. The first approach considers functions as represented by computable analytic functions. The second considers arbitrary computable functions of recursive real numbers. In each case we find natural examples of learnable classes of functions and unlearnable classes of functions.

Complex-valued functionGeneral Computer ScienceReal analysisLearning theoryComputable numberInductive inference0102 computer and information sciences02 engineering and technology01 natural sciencesμ-recursive functionComputable analysisTheoretical Computer ScienceAlgebraμ operatorComputable functionReal-valued computationReal-valued function010201 computation theory & mathematics0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingAlgorithmComputer Science(all)MathematicsTheoretical Computer Science
researchProduct

On the Amount of Nonconstructivity in Learning Recursive Functions

2011

Nonconstructive proofs are a powerful mechanism in mathematics. Furthermore, nonconstructive computations by various types of machines and automata have been considered by e.g., Karp and Lipton [17] and Freivalds [11]. They allow to regard more complicated algorithms from the viewpoint of much more primitive computational devices. The amount of nonconstructivity is a quantitative characterization of the distance between types of computational devices with respect to solving a specific problem. In the present paper, the amount of nonconstructivity in learning of recursive functions is studied. Different learning types are compared with respect to the amount of nonconstructivity needed to lea…

μ operatorClass (set theory)TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGESTheoretical computer sciencePrimitive recursive functionData_CODINGANDINFORMATIONTHEORYInductive reasoningMathematical proofUpper and lower boundsAlgorithmμ-recursive functionAutomatonMathematics
researchProduct

Learning small programs with additional information

1997

This paper was inspired by [FBW 94]. An arbitrary upper bound on the size of some program for the target function suffices for the learning of some program for this function. In [FBW 94] it was discovered that if “learning” is understood as “identification in the limit,” then in some programming languages it is possible to learn a program of size not exceeding the bound, while in some other programming languages this is not possible.

Theoretical computer sciencebusiness.industryComputer sciencemedia_common.quotation_subjectInductive reasoningMachine learningcomputer.software_genreUpper and lower boundsIdentification (information)Recursive functionsArtificial intelligenceLimit (mathematics)businessFunction (engineering)computermedia_common
researchProduct

Probabilistic limit identification up to “small” sets

1996

In this paper we study limit identification of total recursive functions in the case when “small” sets of errors are allowed. Here the notion of “small” sets we formalize in a very general way, i.e. we define a notion of measure for subsets of natural numbers, and we consider as being small those sets, which are subsets of sets with zero measure.

Discrete mathematicsIdentification (information)Zero (complex analysis)Recursive functionsNatural numberLimit (mathematics)Measure (mathematics)Mathematics
researchProduct

Transformations that preserve learnability

1996

We consider transformations (performed by general recursive operators) mapping recursive functions into recursive functions. These transformations can be considered as mapping sets of recursive functions into sets of recursive functions. A transformation is said to be preserving the identification type I, if the transformation always maps I-identifiable sets into I-identifiable sets.

Computer scienceLearnabilityType (model theory)Inductive reasoningAlgebraTuring machinesymbols.namesakeIdentification (information)TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGESTransformation (function)TheoryofComputation_LOGICSANDMEANINGSOFPROGRAMSRecursive functionssymbolsInitial segment
researchProduct

Learning with confidence

1996

Herein we investigate learning in the limit where confidence in the current conjecture accrues with time. Confidence levels are given by rational numbers between 0 and 1. The traditional requirement that for learning in the limit is that a device must converge (in the limit) to a correct answer. We further demand that the associated confidence in the answer (monotonically) approach 1 in the limit. In addition to being a more realistic model of learning, our new notion turns out to be a more powerful as well. In addition, we give precise characterizations of the classes of functions that are learnable in our new model(s).

Discrete mathematicsRational numberConjectureCurrent (mathematics)Recursive functionsMonotonic functionLimit (mathematics)Inductive reasoningMathematics
researchProduct

Dual types of hypotheses in inductive inference

2006

Several well-known inductive inference strategies change the actual hypothesis only when they discover that it “provably misclassifies” an example seen so far. This notion is made mathematically precise and its general power is characterized. In spite of its strength it is shown that this approach is not of “universal” power. Consequently, then hypotheses are considered which “unprovably misclassify” examples and the properties of this approach are studied. Among others it turns out that this type is of the same power as monotonic identification. Finally, it is shown that “universal” power can be achieved only when an unbounded number of alternations of these dual types of hypotheses is all…

Identification (information)Theoretical computer scienceComputer scienceRecursive functionsSpiteMonotonic functionInductive reasoningType (model theory)Dual (category theory)Power (physics)
researchProduct

Inductive inference of recursive functions: Qualitative theory

2005

This survey contains both old and very recent results in non-quantitative aspects of inductive inference of total recursive functions. The survey is not complete. The paper was written to stress some of the main results in selected directions of research performed at the University of Latvia rather than to exhaust all of the obtained results. We concentrated on the more explored areas such as the inference of indices in non-Goedel computable numberings, the inference of minimal Goedel numbers, and the specifics of inference of minimal indices in Kolmogorov numberings.

Turing machinesymbols.namesakeTheoretical computer scienceInductive biasInductive probabilitysymbolsRecursive functionsInferenceInductive reasoningGödel's incompleteness theoremsQualitative theoryMathematics
researchProduct

Unions of identifiable classes of total recursive functions

1992

J.Barzdin [Bar74] has proved that there are classes of total recursive functions which are EX-identifiable but their union is not. We prove that there are no 3 classes U1, U2, U3 such that U1∪U2,U1∪U3 and U2∪U3 would be in EX but U1∪U2∪U3∉ EX. For FIN-identification there are 3 classes with the above-mentioned property and there are no 4 classes U1, U2, U3, U4 such that all 4 unions of triples of these classes would be identifiable but the union of all 4 classes would not. For identification with no more than p minchanges a (2p+2−1)-tuple of such classes do exist but there is no (2p+2)-tuple with the above-mentioned properly.

CombinatoricsIdentification (information)Property (philosophy)Recursive functionsTupleMathematics
researchProduct

Error detecting in inductive inference

1995

Several well-known inductive inference strategies change the actual hypothesis only when they discover that it “provably misclassifies” an example seen so far. This notion is made mathematically precise and its general power is characterized. In spite of its strength it is shown that this approach is not of universal power. Consequently, then hypotheses are considered which “unprovably misclassify” examples and the properties of this approach are studied. Among others it turns out that this type is of the same power as monotonic identification. Then it is shown that universal power can be achieved only when an unbounded number of alternations of these dual types of hypotheses is allowed. Fi…

Identification (information)Computer scienceSpiteRecursive functionsMonotonic functionInductive reasoningType (model theory)AlgorithmDual (category theory)Power (physics)
researchProduct