Learning Concept Descriptions with Typed Evolutionary
Programming
C. Thie, and C. Giraud-Carrier. IEEE Transactions on Knowledge and Data Engineering, 17 (12):
1664--1677(2005)
Abstract
Examples and concepts in traditional concept learning
tasks are represented with the attribute-value
language. While enabling efficient implementations, we
argue that such propositional representation is
inadequate when data is rich in structure. This paper
describes STEPS, a strongly-typed evolutionary
programming system designed to induce concepts from
structured data. STEPS' higher-order logic
representation language enhances expressiveness, while
the use of evolutionary computation dampens the effects
of the corresponding explosion of the search space.
Results on the PTE2 challenge, a major real-world
knowledge discovery application from the molecular
biology domain, demonstrate promise.
%0 Journal Article
%1 10.1109/TKDE.2005.199
%A Thie, Claire J.
%A Giraud-Carrier, Christophe
%C Los Alamitos, CA, USA
%D 2005
%I IEEE Computer Society
%J IEEE Transactions on Knowledge and Data Engineering
%K Concept STGP, algorithms, evolutionary genetic learning, programming programming, typed
%N 12
%P 1664--1677
%T Learning Concept Descriptions with Typed Evolutionary
Programming
%U http://doi.ieeecomputersociety.org/10.1109/TKDE.2005.199
%V 17
%X Examples and concepts in traditional concept learning
tasks are represented with the attribute-value
language. While enabling efficient implementations, we
argue that such propositional representation is
inadequate when data is rich in structure. This paper
describes STEPS, a strongly-typed evolutionary
programming system designed to induce concepts from
structured data. STEPS' higher-order logic
representation language enhances expressiveness, while
the use of evolutionary computation dampens the effects
of the corresponding explosion of the search space.
Results on the PTE2 challenge, a major real-world
knowledge discovery application from the molecular
biology domain, demonstrate promise.
@article{10.1109/TKDE.2005.199,
abstract = {Examples and concepts in traditional concept learning
tasks are represented with the attribute-value
language. While enabling efficient implementations, we
argue that such propositional representation is
inadequate when data is rich in structure. This paper
describes STEPS, a strongly-typed evolutionary
programming system designed to induce concepts from
structured data. STEPS' higher-order logic
representation language enhances expressiveness, while
the use of evolutionary computation dampens the effects
of the corresponding explosion of the search space.
Results on the PTE2 challenge, a major real-world
knowledge discovery application from the molecular
biology domain, demonstrate promise.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Los Alamitos, CA, USA},
author = {Thie, Claire J. and Giraud-Carrier, Christophe},
biburl = {https://www.bibsonomy.org/bibtex/2ba3474451cf7c0884c0ef24fbc8dc43f/brazovayeye},
interhash = {1465071f688fa43e14673366db31b7e9},
intrahash = {ba3474451cf7c0884c0ef24fbc8dc43f},
issn = {1041-4347},
journal = {IEEE Transactions on Knowledge and Data Engineering},
keywords = {Concept STGP, algorithms, evolutionary genetic learning, programming programming, typed},
notes = {Claire Julia Kennedy},
number = 12,
pages = {1664--1677},
publisher = {IEEE Computer Society},
timestamp = {2008-06-19T17:53:07.000+0200},
title = {Learning Concept Descriptions with Typed Evolutionary
Programming},
url = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2005.199},
volume = 17,
year = 2005
}