Inductive inference: Theory and methods
D Angluin, CH Smith - ACM computing surveys (CSUR), 1983 - dl.acm.org
There has been a great deal of theoretical and experimental work in computer science on
inductive inference systems, that is, systems that try to infer general rules from examples …
inductive inference systems, that is, systems that try to infer general rules from examples …
Computational limitations on learning from examples
L Pitt, LG Valiant - Journal of the ACM (JACM), 1988 - dl.acm.org
The computational complexity of learning Boolean concepts from examples is investigated. It
is shown for various classes of concept representations that these cannot be learned …
is shown for various classes of concept representations that these cannot be learned …
Probabilistic inductive inference
L Pitt - Journal of the ACM (JACM), 1989 - dl.acm.org
Inductive inference machines construct programs for total recursive functions given only
example values of the functions. Probabilistic inductive inference machines are defined, and …
example values of the functions. Probabilistic inductive inference machines are defined, and …
Probability and plurality for aggregations of learning machines
L Pitt, CH Smith - Information and Computation, 1988 - Elsevier
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 …
probabilistic inference and team inference. In many cases, but not all, probabilism can be …
Learning recursive functions: A survey
T Zeugmann, S Zilles - Theoretical Computer Science, 2008 - Elsevier
Studying the learnability of classes of recursive functions has attracted considerable interest
for at least four decades. Starting with Gold's (1967) model of learning in the limit, many …
for at least four decades. Starting with Gold's (1967) model of learning in the limit, many …
On the power of inductive inference from good examples
R Freivalds, EB Kinber, R Wiehagen - Theoretical Computer Science, 1993 - Elsevier
The usual information in inductive inference available for the purposes of identifying an
unknown recursive function f is the set of all input/output examples (x, f (x)), n εN. In contrast …
unknown recursive function f is the set of all input/output examples (x, f (x)), n εN. In contrast …
A characterization of probabilistic inference
L Pitt - 25th Annual Symposium onFoundations of Computer …, 1984 - ieeexplore.ieee.org
Inductive Inference Machines (IlMs) attempt to identify functions given only input-output pairs
of the functions. Probabilistic IlMs are defined, as is the probability that a probabilistic IlM …
of the functions. Probabilistic IlMs are defined, as is the probability that a probabilistic IlM …
On the power of probabilistic strategies in inductive inference
R Wiehagen, R Freivalds, EB Kinber - Theoretical Computer Science, 1983 - Elsevier
Inductive inference of programs of recursive functions from input/output examples by
probabilistic strategies with an a priori bound n ϵ N of changes of hypotheses is …
probabilistic strategies with an a priori bound n ϵ N of changes of hypotheses is …
The synthesis of language learners
An index for an re class of languages (by definition) is a procedure which generates a
sequence of grammars defining the class. An index for an indexed family of languages (by …
sequence of grammars defining the class. An index for an indexed family of languages (by …
Breaking the probability ½ barrier in FIN-type learning
R Daley, B Kalyanasundaram… - Proceedings of the fifth …, 1992 - dl.acm.org
We show that for every probabilistic FIN-type learner with success ratio greater than 24/49,
there is another probabilistic FIN-type learner with success ratio 1/2 that simulates the …
there is another probabilistic FIN-type learner with success ratio 1/2 that simulates the …