Interpretability of artificial hydrocarbon networks for breast cancer classification

Show simple item record

dc.contributor.author Ponce Espinosa, Hiram Eredín
dc.contributor.author Martínez Villaseñor, María de Lourdes Guadalupe
dc.creator MARÍA DE LOURDES GUADALUPE MARTÍNEZ VILLASEÑOR:241561
dc.date.accessioned 2018-03-02T15:10:16Z
dc.date.available 2018-03-02T15:10:16Z
dc.date.issued 2017
dc.identifier http://dx.doi.org/10.1109/IJCNN.2017.7966301
dc.identifier.citation Ponce Espinosa, H. E. y Martínez Villaseñor, M. L. (2017). Interpretability of artificial hydrocarbon networks for breast cancer classification. En Proceedings of the International Joint Conference on Neural Networks (pp. 3535-3542). Institute of Electrical and Electronics Engineers. DOI: 10.1109/IJCNN.2017.7966301 es_ES, en_US
dc.identifier.isbn 9781509061815 es_ES, en_US
dc.identifier.other Campus Ciudad de México es_ES, en_US
dc.identifier.uri http://scripta.up.edu.mx/xmlui/handle/123456789/4478
dc.description.abstract In machine learning, interpretability refers to understand the underlying behavior of the prediction of a model in order to identify diagnosis criteria and/or new rules from its output. Interpretability contributes to increase the usability of the method. Also, it is relevant in decision support systems, such as in medical applications. White-box models like tree-based, rule-based and linear models are considered the most comprehensible, but less accurate or simplistic. In contrast, black-box models like nonlinear and ensemble models are more accurate hence more complex to interpret. Thus, a trade-off between accuracy and interpretability is often made when building models to support human experts in a decision-making process. Artificial hydrocarbon networks (AHN) is a supervised learning method that has been proved to be very effective for regression and classification problems. In fact, its training process suggests a kind of interpretability. Thus, the objective of this work is to present first efforts proving the capacity of artificial hydrocarbon networks (AHN) to deliver interpretable models. In order to assess the interpretability of AHN, we address the breast cancer problem using a public dataset. Results showed that AHN can be transformed in treebased and rule-based models preserving high accuracy in the output classification. © 2017 IEEE. es_ES, en_US
dc.description.statementofresponsibility Investigadores es_ES, en_US
dc.description.statementofresponsibility Estudiantes sp
dc.description.statementofresponsibility Maestros sp
dc.description.tableofcontents Ingeniería es_ES, en_US
dc.language Español es_ES, en_US
dc.publisher Institute of Electrical and Electronics Engineers es_ES, en_US
dc.publisher Proceedings of the International Joint Conference on Neural Networks
dc.publisher Institute of Electrical and Electronics Engineers Inc.
dc.relation Versión del editor es_ES, en_US
dc.rights Acceso Restringido es_ES, en_US
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/4.0/ es_ES, en_US
dc.subject Artificial intelligence es_ES, en_US
dc.subject Decision making es_ES, en_US
dc.subject Decision support systems es_ES, en_US
dc.subject Diagnosis es_ES, en_US
dc.subject Diseases es_ES, en_US
dc.subject Economic and social effects es_ES, en_US
dc.subject Hydrocarbons; Medical applications es_ES, en_US
dc.subject Supervised learning es_ES, en_US
dc.subject Breast cancer classifications es_ES, en_US
dc.subject Decision making process es_ES, en_US
dc.subject Diagnosis criteria es_ES, en_US
dc.subject Interpretability es_ES, en_US
dc.subject Rule-based models es_ES, en_US
dc.subject Supervised learning methods es_ES, en_US
dc.subject Training process es_ES, en_US
dc.subject White-box models es_ES, en_US
dc.subject Learning systems es_ES, en_US
dc.subject.classification INGENIERIA Y TECNOLOGIA es_ES, en_US
dc.subject.classification MEDICINA Y CIENCIAS DE LA SALUD sp
dc.title Interpretability of artificial hydrocarbon networks for breast cancer classification es_ES, en_US
dc.type contribución a congreso es_ES, en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Acceso Restringido Except where otherwise noted, this item's license is described as Acceso Restringido

Search Scripta


Advanced Search

Browse

My Account