DMCA
Iterative Learning from Positive Data and Negative Counterexamples (2007)
| Citations: | 2 - 2 self |
BibTeX
@MISC{Jain07iterativelearning,
author = {Sanjay Jain and Efim Kinber},
title = {Iterative Learning from Positive Data and Negative Counterexamples},
year = {2007}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A model for learning in the limit is defined where a (so-called iterative) learner gets all positive examples from the target language, tests every new conjecture with a teacher (oracle) if it is a subset of the target language (and if it is not, then it receives a negative counterexample), and uses only limited long-term memory (incorporated in conjectures). Three variants of this model are compared: when a learner receives least negative counterexamples, the ones whose size is bounded by the maximum size of input seen so far, and arbitrary ones. A surprising result is that sometimes absence of bounded counterexamples can help an iterative learner whereas arbitrary counterexamples are useless. We also compare our learnability model with other relevant models of learnability in the limit, study how our model works for indexed classes of recursive languages, and show that learners in our model can work in non-U-shaped way — never abandoning the first right conjecture.
Keyphrases
negative counterexample iterative learning positive data target language new conjecture bounded counterexample learnability model non-u-shaped way iterative learner whereas arbitrary counterexample maximum size positive example recursive language relevant model first right conjecture limited long-term memory surprising result arbitrary one indexed class so-called iterative
