Inductive Inference: Theory and Methods

@article{Angluin1983InductiveIT,
  title={Inductive Inference: Theory and Methods},
  author={Dana Angluin and Carl H. Smith},
  journal={ACM Comput. Surv.},
  year={1983},
  volume={15},
  pages={237-269}
}
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. However, a complete and applicable theory of such systems is still a distant goal. This survey highlights and explains the main ideas that have been developed in the study of inductive inference, with special emphasis on the relations between the general theory and the specific algorithms and implementations. 154… 
Inductive Inference Machines That Can Refute Hypothesis Spaces
TLDR
It is pointed out that the essence of a logic of machine discovery is the refutability of the entire spaces of hypotheses, and the framework of inductive inference of length-bounded elementary formal systems (EFS's) is discussed, which are a kind of logic programs over strings of characters and correspond to context-sensitive grammars in Chomsky hierarchy.
Robust separations in inductive inference
  • Mark A. Fulk
  • Mathematics, Computer Science
    Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science
  • 1990
TLDR
The author refutes BarZdin's conjecture and proposes a new line of research examining robust separations which are defined using a strengthening of Barzdin's original idea.
Inductive Inference by Refinement
A model is presented for the class of inductive inference problems that are solved by refinement algorithms - that is, algorithms that modify a hypothesis by making it more general or more specific
From inductive inference to algorithmic learning theory
TLDR
Two phenomena which were discovered in pure recursion-theoretic inductive inference, namely inconsistent learning and learning from good examples, are presented.
From Inductive Inference to Algorithmic Learning Theory
TLDR
Inductive inference can be understood and used as a source of potent ideas guiding both research and applications in algorithmic learning theory.
A Thesis in Inductive Inference
  • Rolf Wiehagen
  • Computer Science
    Nonmonotonic and Inductive Logic
  • 1990
TLDR
The following thesis was stated: Any class of recursive functions which is identifiable at all can always be identified by an enumeratively working strategy and the identification canAlways be realized with respect to a suitable nonstandard (i.e. non-Godel) numbering.
On the Power of Inductive Inference from Good Examples
TLDR
It is shown that it is considerably more powerful to work with finite sets of “good” examples even when these good examples are required to be effectively computable.
On the Complexity of Inductive Inference
TLDR
An axiomatization of the notion of the complexity of inductive inference is developed and several results are presented which both resemble and contrast with results obtainable for the axiomatic computational complexity of recursive functions.
Inductive Inference on the Base of Fixed Point Theory
TLDR
An inductive inference method is presented as to find the hypothetical equation system from the increasing set of experimentel data such that its solutions would fit all the information.
Precise induction from statistical data
TLDR
This paper presents an algorithm that uses statistics to infer Boolean predicates, and an investigation of what statistics are relevant for such inference, and what predicates can be inferred.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 191 REFERENCES
Toward a Mathematical Theory of Inductive Inference
TLDR
This paper investigates the theoretical capabilities and limitations of a computer to infer such sequences and design Turing machines that in principle are extremely powerful for this purpose and place upper bounds on the capabilities of machines that would do better.
Research in the theory of inductive inference by GDR mathematicians - A survey
Recent results in the theory of inductive inference are summarized. They concern deciphering of automata, language identification, prediction of functions, inference with additional information,
Some Natural Properties of Strong-Identification in Inductive Inference
  • E. Minicozzi
  • Computer Science, Mathematics
    Theor. Comput. Sci.
  • 1976
TLDR
The problem of inducing an algorithm for a partial recursive function from the analysis of its graph or loosely speaking of “learning” it, is discussed.
Comparison of Identification Criteria for Machine Inductive Inference
Abstract A natural ωpLω+1 hierarchy of successively more general criteria of success for inductive inference machines is described based on the size of sets of anomalies in programs synthesized by
Inductive Inference of Formal Languages from Positive Data
  • D. Angluin
  • Computer Science, Mathematics
    Inf. Control.
  • 1980
TLDR
A theorem characterizing when an indexed family of nonempty recursive formal languages is inferrable from positive data is proved, and other useful conditions for inference frompositive data are obtained.
Inference for Regular Bilanguages
TLDR
The solution makes use of the Pair-Quere notion of homomorphism of binoids and permits the synthesis of a class of inference algorithms, which this paper studies.
A Formal Theory of Inductive Inference. Part II
1. Summary In Part I, four ostensibly different theoretical models of induction are presented, in which the problem dealt with is the extrapolation of a very long sequence of symbols—presumably
Inductive inference theory: a unified approach to problems in pattern recognition and artificial intelligence
TLDR
The theory is used to obtain the a priori probabilities that are necessary in the application of stochastic languages to pattern recognition and A.I. theory to make critical decisions.
Learning and Inductive Inference
TLDR
A simple model that serves to generate a taxonomy of learning systems is presented and the explication and clarification of four methods of learning single concepts are explained.
Anomaly hierarchies of mechanized inductive inference
TLDR
An inductive inference machine is defined to be an algorithmic device with no bounds on how much time and memory resource it shall use, which takes as its input the graph of a function, and which, from time to time, as it's receiving its inputs, outputs computer programs.
...
1
2
3
4
5
...