On learning of functions refutably

Jain, Sanjay; Kinber, Efim; Wiehagen, Rolf; Zeugmann, Thomas

doi:10.1016/s0304-3975(02)00421-8

Cited by 4 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in [9], the cases in which a refutation has to take place, have been tailored towards more realistic needs. Jain et al [10] considered weaker variants of refutation. Also, a lot of other investigations of the model of refutation, as well as applications in other scenarios, have taken place (cf., e.g., [11][12][13][14]).…”

Section: Machine Self-assessmentmentioning

confidence: 99%

Reflective inductive inference of recursive functions

Grieser

2008

Theoretical Computer Science

View full text Add to dashboard Cite

In this paper, we investigate reflective inductive inference of recursive functions. A reflective IIM is a learning machine that is additionally able to assess its own competence.First, we formalize reflective learning from arbitrary, and from canonical, example sequences. Here, we arrive at four different types of reflection: reflection in the limit, optimistic, pessimistic and exact reflection.Then, we compare the learning power of reflective IIMs with each other as well as with the one of standard IIMs for learning in the limit, for consistent learning of three different types, and for finite learning.

show abstract

Section: Machine Self-assessmentmentioning

confidence: 99%

Reflective inductive inference of recursive functions

Grieser

2008

Theoretical Computer Science

View full text Add to dashboard Cite

show abstract

“…While a refuting learner continues forever to output refutation symbols after having output a refutation symbol once, a limitrefuting learner might alternate between indices and refutation symbols in an arbitrary way before converging. Another even more liberal model where refuting means to output a refutation symbol infinitely often can be shown [7,8,11] to be equivalent to Minicozzi's [12] concept of reliable learning.…”

Section: Characterizations Of Refutable and Reliable Learningmentioning

confidence: 99%

“…Limit-refuting learning is considered by Jain et al [7,8] in the setting of function learning from informant and by Merkle and Stephan [11] in the setting of set learning from text. Note that Jain et al focus on a variant of limit-refuting learning where the learner only has to refute all recursive functions that are not learned.…”

Section: Characterizations Of Refutable and Reliable Learningmentioning

confidence: 99%

Trees and learning

Merkle

Stephan

2004

Journal of Computer and System Sciences

View full text Add to dashboard Cite

We characterize FIN-, EX-and BC-learning, as well as the corresponding notions of team learning, in terms of isolated branches on effectively given sequences of trees. The more restrictive models of FINlearning and strong-monotonic BC-learning are characterized in terms of isolated branches on a single tree. Furthermore, we discuss learning with additional information where the learner receives an index for a strongly recursive tree such that the function to be learned is isolated on this tree. We show that EXlearning with this type of additional information is strictly more powerful than EX-learning. r

show abstract

On the Interplay Between Inductive Inference of Recursive Functions, Complexity Theory and Recursive Numberings

Zeugmann

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

On learning of functions refutably

Cited by 4 publications

References 31 publications

Reflective inductive inference of recursive functions

Reflective inductive inference of recursive functions

Trees and learning

On the Interplay Between Inductive Inference of Recursive Functions, Complexity Theory and Recursive Numberings

Contact Info

Product

Resources

About