|
Formal Methods in Computing (Most of the papers antecedent to 1995 are not included in the list) |
|||
| FRAMES NO FRAME | ||||
| Berardi-deLiguoro:CSL12 (In proceedings) | |
| Author(s) | Stefano Berardi and Ugo de' Liguoro |
| Title | « Knowledge Spaces and the Completeness of Learning Strategies » |
| In | Computer Science Logic (CSL'12) - 26th International Workshop/21st Annual Conference of the EACSL, CSL 2012, September 3-6, 2012, Fontainebleau, France |
| Series | LIPIcs |
| Editor(s) | Patrick Cégielski and Arnaud Durand |
| Volume | 16 |
| Page(s) | 77-91 |
| Year | 2012 |
| Publisher | Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik |
| ISBN number | 978-3-939897-42-2 |
| Abstract | |
| We propose a theory of learning aimed to formalize some ideas underlying Coquand's game semantics and Krivine's realizability of classical logic. We introduce a notion of knowledge state together with a new topology, capturing finite positive and negative information that guides a learning strategy. We use a leading example to illustrate how non-constructive proofs lead to continuous and effective learning strategies over knowledge spaces, and prove that our learning semantics is sound and complete w.r.t. classical truth, as it is the case for Coquand's and Krivine's approaches. | |
Download the complete article:
| BibTeX code |
@inproceedings{Berardi-deLiguoro:CSL12,
volume = {16},
author = {Stefano Berardi and Ugo de' Liguoro},
series = {LIPIcs},
booktitle = {{Computer Science Logic (CSL'12) - 26th International
Workshop/21st Annual Conference of the EACSL, CSL 2012, September
3-6, 2012, Fontainebleau, France}},
editor = {Patrick C{\'e}gielski and Arnaud Durand},
title = {{Knowledge Spaces and the Completeness of Learning Strategies}},
localfile = {http://www.di.unito.it/~deligu/papers/KnowSpace.pdf},
isbn = {978-3-939897-42-2},
abstract = {We propose a theory of learning aimed to formalize some ideas
underlying Coquand's game semantics and Krivine's realizability of
classical logic. We introduce a notion of knowledge state together
with a new topology, capturing finite positive and negative
information that guides a learning strategy. We use a leading
example to illustrate how non-constructive proofs lead to
continuous and effective learning strategies over knowledge
spaces, and prove that our learning semantics is sound and
complete w.r.t. classical truth, as it is the case for Coquand's
and Krivine's approaches.},
tag = {CSL'12},
publisher = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik},
year = {2012},
pages = {77-91},
}
|
Formal Methods in Computing (Most of the papers antecedent to 1995 are not included in the list) |
|||
| FRAMES NO FRAME | ||||
This document was generated by bib2html 3.3.
(Modified by Luca Paolini, under the GNU General Public License)
