- 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 However, these architectures have not surpassed hand-craft models working with outdated problems with datasets of icon images.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)",
