Abstract | ||
---|---|---|
The consistency dimension, in several variants, is a recently introduced parameter useful for the study of polynomial query learning models. It characterizes those representation classes that are learnable in the corresponding models. By selecting an abstract enough concept of representation class, we formalize the intuitions that these dimensions relate to compactness issues, both in Logic and in a specific topological space. Thus, we are lead to the introduction of Quantitative Compactness notions, which simultaneously have a clear topological meaning and still characterize polynomial query learnable representation classes of boolean functions. They might have relevance elsewhere too. Their study is still ongoing, so that this paper is in a sense visionary, and might be flawed. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1007/3-540-48168-0_2 | CSL |
Keywords | Field | DocType |
representation class,abstract enough concept,polynomial query,consistency dimension,compactness issue,quantitative compactness notion,boolean function,query learning,polynomial query learnable representation,specific topological space,clear topological meaning,topological space | Boolean function,Query learning,Discrete mathematics,Polynomial,Topological space,Representation class,Computer science,Propositional calculus,Intuition,Compact space | Conference |
ISBN | Citations | PageRank |
3-540-66536-6 | 1 | 0.36 |
References | Authors | |
6 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
José L. Balcázar | 1 | 701 | 62.06 |