Systems that learn: an introduction to learning theory for cognitive and computer scientists
Systems that learn: an introduction to learning theory for cognitive and computer scientists
Recursively enumerable sets and degrees
Recursively enumerable sets and degrees
Inductive inference of monotonic formal systems from positive data
New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
Handbook of theoretical computer science (vol. B)
Journal of the ACM (JACM)
Towards a mathematical theory of machine discovery from facts
Theoretical Computer Science - Special issue on algorithmic learning theory
Elementary formal systems, intrinsic complexity, and procrastination
Information and Computation
Journal of Computer and System Sciences - Fourteenth ACM SIGACT-SIGMOD-SIGART symposium on principles of database systems
Locally Threshold Testable Languages of Infinite Words
STACS '93 Proceedings of the 10th Annual Symposium on Theoretical Aspects of Computer Science
Inductive Inference Machines That Can Refute Hypothesis Spaces
ALT '93 Proceedings of the 4th International Workshop on Algorithmic Learning Theory
Machine Discovery in the Presence of Incomplete or Ambiguous Data
AII '94 Proceedings of the 4th International Workshop on Analogical and Inductive Inference: Algorithmic Learning Theory
Reflecting and Self-Confident Inductive Inference Machines
ALT '95 Proceedings of the 6th International Conference on Algorithmic Learning Theory
Reflecting Inductive Inference Machines and Its Improvement by Therapy
ALT '96 Proceedings of the 7th International Workshop on Algorithmic Learning Theory
Learning power and language expressiveness
Theoretical Computer Science - Australasian computer science
On learning of functions refutably
Theoretical Computer Science - Selected papers in honour of Setsuo Arikawa
Learning by switching type of information
Information and Computation
Journal of Computer and System Sciences
On the learnability of vector spaces
Journal of Computer and System Sciences
Reflective inductive inference of recursive functions
Theoretical Computer Science
Hi-index | 0.00 |
We consider, within the framework of inductive inference, the concept of refuting learning as introduced by Mukouchi and Arikawa, where the learner is not only required to learn all concepts in a given class but also has to explicitly refute concepts outside the class.In the first part of the paper, we consider learning from text and introduce a concept of limit-refuting learning that is intermediate between refuting learning and reliable learning. We give characterizations for these concepts and show some results about their relative strength and their relation to confident learning.In the second part of the paper we consider learning from texts that for some k contain all positive Πk-formulae that are valid in the standard structure determined by the set to be learned. In this model, the following results are shown. For the language with successor, any countable axiomatizable class can be limit-refuting learned from Π1-texts. For the language with successor and order, any countable axiomatizable class can be reliably learned from Π1-texts and can be limit-refuting learned from Π2-texts, whereas the axiomatizable class of all finite sets cannot be limit-refuting learned from Π1-texts. For the full language of arithmetic, which contains in addition plus and times, for any even k there is an axiomatizable class that can be limit-refuting learned from Πk+1-texts but not from Πk-texts. A similar result with k + 3 in place of k + 1 holds with respect to the language of Presburger's arithmetic.