Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 891440

Amplitude-oriented mixed-type CGP classification


Knežević, Karlo; Picek, Stjepan; Miller, Julian Francis
Amplitude-oriented mixed-type CGP classification // GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion
Berlin, Njemačka, 2017. str. 1415-1418 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 891440 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Amplitude-oriented mixed-type CGP classification

Autori
Knežević, Karlo ; Picek, Stjepan ; Miller, Julian Francis

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion / - , 2017, 1415-1418

ISBN
978-1-4503-4939-0

Skup
The Genetic and Evolutionary Computation Conference, GECCO 2017

Mjesto i datum
Berlin, Njemačka, 15-19.07.2017

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Mixed-type CGP, Classification, Binary, Multi-class, Amplitude, L1-regularization

Sažetak
Evolutionary algorithms have proved their worth on various optimization problems over the course of years. However, some techniques like genetic programming (GP) and Cartesian genetic programming (CGP) are not restricted only to optimization problems but can be also used in classification tasks. In this paper, we consider mixed-type CGP (MT- CGP) and test it on a number of benchmark binary and multi-class problems. Following that, we introduce a new representation for our algorithm where each node also has an accompanying weight factor called the amplitude. Our results suggest that this version of CGP is more powerful and able to obtain higher accuracies when compared to the mixed-type CGP or the standard CGP. Finally, we introduce the L1 regularization into MT-CGP in order to facilitate even further feature reduction.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekti:
HRZZ-IP-2014-09-4882 - Heuristička optimizacija u kriptologiji (EvoCrypt) (Jakobović, Domagoj, HRZZ - 2014-09) ( POIROT)

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Karlo Knežević (autor)

Avatar Url Stjepan Picek (autor)

Poveznice na cjeloviti tekst rada:

Pristup cjelovitom tekstu rada dl.acm.org

Citiraj ovu publikaciju:

Knežević, Karlo; Picek, Stjepan; Miller, Julian Francis
Amplitude-oriented mixed-type CGP classification // GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion
Berlin, Njemačka, 2017. str. 1415-1418 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Knežević, K., Picek, S. & Miller, J. (2017) Amplitude-oriented mixed-type CGP classification. U: GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion.
@article{article, year = {2017}, pages = {1415-1418}, keywords = {Mixed-type CGP, Classification, Binary, Multi-class, Amplitude, L1-regularization}, isbn = {978-1-4503-4939-0}, title = {Amplitude-oriented mixed-type CGP classification}, keyword = {Mixed-type CGP, Classification, Binary, Multi-class, Amplitude, L1-regularization}, publisherplace = {Berlin, Njema\v{c}ka} }
@article{article, year = {2017}, pages = {1415-1418}, keywords = {Mixed-type CGP, Classification, Binary, Multi-class, Amplitude, L1-regularization}, isbn = {978-1-4503-4939-0}, title = {Amplitude-oriented mixed-type CGP classification}, keyword = {Mixed-type CGP, Classification, Binary, Multi-class, Amplitude, L1-regularization}, publisherplace = {Berlin, Njema\v{c}ka} }




Contrast
Increase Font
Decrease Font
Dyslexic Font