N-Learners Problem: Fusion of Concepts. MARTIN. MA. RIETrA. I'. Nageswara S. V ... We are given N learners each capable of learning concepts (subsets) of a domain.

Given N learners each capable of learning concepts (subsets) in the sense of Valiant (1985), we are interested in combining them using a single fuser.

Addresses the N-learners problem (a special case of data fusion) where each learner is capable of learning subsets of a domain set X. In open fusion the ...

We consider two cases: open and closed fusion. In open fusion the fuser is given the sample and the hypotheses of the individual learners; we show that the ...

and the hypotheses of the individual learners; we show that a fusion rule can be obtained by formulating this problem as another learning problem.

We are interested in combining the N learners using a single fuser or consolidator. We consider the paradigm of passive fusion, where each learner is first ...

By using a linear threshold fusion function (of the outputs of individual learners) it is shown that the composite system can be made better than the best ...

Then the question of combining these learners using a fuser to make the overall system better than any of the learners, has been studied by Rao.

A system of Probably Approximately Correct (PAC) learners, where each learner had produced a hypothesis by employing empirical risk minimization methods, ...

Given N learners each capable of learning concepts (subsets) in the sense of Valiant, we are interested in combining them using a single fuser, We consider two ...