Brain programming is immune to adversarial attacks: Towards accurate and robust image classification using symbolic learning

Ibarra-Vazquez, Gerardo; Olague, Gustavo; Chan-Ley, Mariana; Puente, Cesar; Soubervielle‐Montalvo, Carlos

doi:10.1016/j.swevo.2022.101059

Cited by 13 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GP starts the cycle (17). The conditional if has a negative value only in the first loop; its function is to create a new generation from the current one (18)(19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29).…”

Section: Appendix Amentioning

confidence: 99%

“…The second cycle creates new generations of the population (18)(19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29). The parents chrom array ( 19) is emptied.…”

Section: Appendix Amentioning

confidence: 99%

“…Next, the best masks of the MCG are extracted (16). In the next three lines, we execute rescaling processes and grayscale conversions of the final mask (17)(18)(19).…”

Section: Appendix Amentioning

confidence: 99%

“…The scores and characteristics are readjusted (12)(13)(14) in the following three lines. Then the MCG results are converted into masks (15)(16)(17)(18), filtered, and saved to a file (19)(20)(21). Finally, the masks, candidates, segment numbers, and features are returned (23).…”

Section: Outputmentioning

confidence: 99%

“…Iqbal et al introduce the idea of applying learning classifier systems to SOD research [18]. Brain programming has proved its robustness against adversarial attacks, a hot topic in machine learning, for the problem of image classification [19]. Finally, the honeybee search algorithm is applied to 3D reconstruction and visual tracking by [20,21].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automated Design of Salient Object Detection Algorithms with Brain Programming

et al. 2022

Self Cite

View full text Add to dashboard Cite

Despite recent improvements in computer vision, artificial visual systems’ design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain’s inner workings. Progress in this research area follows the traditional path of hand-made designs using neuroscience knowledge or, more recently, deep learning, a particular branch of machine learning. Recently, a different approach based on genetic programming appeared to enhance handcrafted techniques following two different strategies. The first method follows the idea of combining previous hand-made methods through genetic programming and fuzzy logic. The second approach improves the inner computational structures of basic hand-made models through artificial evolution. This research proposes expanding the artificial dorsal stream using a recent proposal based on symbolic learning to solve salient object detection problems following the second technique. This approach applies the fusion of visual saliency and image segmentation algorithms as a template. The proposed methodology discovers several critical structures in the template through artificial evolution. We present results on a benchmark designed by experts with outstanding results in an extensive comparison with the state of the art, including classical methods and deep learning approaches to highlight the importance of symbolic learning in visual saliency.

show abstract

Section: Appendix Amentioning

confidence: 99%

“…The second cycle creates new generations of the population (18)(19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29). The parents chrom array ( 19) is emptied.…”

Section: Appendix Amentioning

confidence: 99%

“…Next, the best masks of the MCG are extracted (16). In the next three lines, we execute rescaling processes and grayscale conversions of the final mask (17)(18)(19).…”

Section: Appendix Amentioning

confidence: 99%

Section: Outputmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Design of Salient Object Detection Algorithms with Brain Programming

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Resilient Bioinspired Algorithms: A Computer System Design Perspective

Cotta

Olague

2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Resilience can be defined as a system's capability for returning to normal operation after having suffered a disruption. This notion is of the foremost interest in many areas, in particular engineering. We argue in this position paper that is is a crucial property for bioinspired optimization algorithms as well. Following a computer system perspective, we correlate some of the defining requirements for attaining resilient systems to issues, features, and mechanisms of these techniques. It is shown that bioinspired algorithms do not only exhibit a notorious built-in resilience, but that their plasticity also allows accommodating components that may boost it in different ways. We also provide some relevant research directions in this area.

show abstract