Automated Design of Accurate and Robust Image Classifiers with Brain Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.8010
- @InProceedings{Ibarra-Vazquez:2021:ECADA,
-
author = "Gerardo Ibarra-Vazquez and Gustavo Olague and
Cesar Puente and Mariana Chan-Ley and
Carlos Soubervielle-Montalvo",
-
title = "Automated Design of Accurate and Robust Image
Classifiers with Brain Programming",
-
booktitle = "11th Workshop on Evolutionary Computation for the
Automated Design of Algorithms (ECADA)",
-
year = "2021",
-
editor = "Manuel Lopez-Ibanez and Daniel R. Tauritz and
John R. Woodward",
-
address = "internet",
-
series = "GECCO '21",
-
month = jul # " 10-14",
-
organisation = "SIGEVO",
-
publisher = "Association for Computing Machinery",
-
publisher_address = "New York, NY, USA",
-
keywords = "genetic algorithms, genetic programming, ANN, Secure,
Face Recognition, Art Media Categorization, Adversarial
Attacks, Convolutional Neural Networks, Brain
Programming",
-
URL = "http://www.human-competitive.org/sites/default/files/olague-humies2021-final_0.txt",
-
URL = "http://www.human-competitive.org/sites/default/files/olague-geccow2021.pdf",
-
DOI = "doi:10.1145/3449726.3463179",
-
size = "9 pages",
-
abstract = "Foster the mechanical design of artificial vision
requires a delicate balance between high-level
analytical methods and the discovery through
metaheuristics of near-optimal functions working
towards complex visual problems. Evolutionary
computation and swarm intelligence have developed
strategies that automatically design meaningful deep
convolutional neural network architectures to create
better image classifiers. However, these architectures
have not surpassed hand-craft models working with
outdated problems with datasets of icon images.
Nowadays, recent concerns about deep convolutional
neural networks to adversarial attacks in the form of
modifications to the input image can manipulate their
output to make them untrustworthy. Brain programming is
a hyper-heuristic whose aim is to work at a higher
level of abstraction to develop automatically
artificial visual cortex algorithms for a problem
domain like image classification. Our primary goal is
to employ brain programming to design an artificial
visual cortex to produce accurate and robust image
classifiers in two problems. We analyze the final
models designed by brain programming with the
assumption of fooling the system using two adversarial
attacks. In both experiments, brain programming
constructed artificial brain models capable of
competing with hand-crafted deep convolutional neural
networks without any influence in the predictions when
an adversarial attack is present.",
-
notes = "Entered 2021
HUMIES
https://bonsai.auburn.edu/ecada/GECCO2021/index.html
GECCO-2021 A Recombination of the 30th International
Conference on Genetic Algorithms (ICGA) and the 26th
Annual Genetic Programming Conference (GP)",
- }
Genetic Programming entries for
Gerardo Ibarra-Vazquez
Gustavo Olague
Cesar Puente
Mariana Chan-Ley
Carlos Soubervielle-Montalvo
Citations