Abstract
Brain programming is a methodology based on the idea that templates are necessary to describe artificial dorsal and ventral streams and their combination into an artificial visual cortex. We review the main concerns by introducing some initial thoughts about the status of genetic programming and other methodologies related to our research work. This chapter proposes the hierarchical integration of two architectures (templates) to enhance the quality of acquiring artificial visual percepts. We theoretically justified the necessity for designing manual hierarchical architectures. Planning complex structures through inferential knowledge simplify the design while adopting current technology. The methodology base its analysis on providing domain knowledge (neuroscience) at a higher level while looking for better computational structures within a local (lower) level. The efficiency of searching for optimal architectural configurations proceeds from deductive and inductive reasoning. This chapter brings a proposal of abductive reasoning to enrich the brain programming paradigm by taking advantage of computational re-use of dorsal stream discoveries while enhancing the overall complexity of the final proposal. We propose a Visual Turing test to establish the quality of the proposal in comparison with the state of the art. The results show that our methodology can produce consistent outcomes during training and testing, representing significant progress toward thought representation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In linguistics-etymology, people call two or more words in the same language doublets or etymological twins or twinlings when they have different phonological forms but the same etymological root.
- 2.
According to St. Thomas Aquinas, internal senses are common sense, imagination, estimative power, and memory; and external senses are smell, sight, touch, taste, and hearing.
- 3.
CV attempts to recreate the external sense of sight that precedes language; hence representation of thought is the goal we strive to reach by formulating a representation helpful to communicating ideas.
- 4.
The literature treated abduction, retroduction, transduction, and even few-shot learning as similar concepts. While tempting to do so, the advice is to study them as different concepts.
- 5.
CNNs base their computation on correlations, which is why they are invariant to translation and can store a large amount of data.
References
Andrade, E.: Natural abduction: the bridge between individuals choices and the production of evolutionary innovations. Signs 5, 112–146 (2011)
Aquinas, T.: Summa Theologica I q 79 a 10. Gilby, T. (ed.) OP, vol. 60. Blackfriars, Cambridge (1966)
Choi, C.Q.: 7 Revealing Ways AIs Fail. IEEE Spectrum October, pp. 42–47 (2021). https://spectrum.ieee.org/ai-failures
Clemente, E., Olague, G., Dozal, L., Mancilla, M.: Object Recognition with an Optimized Ventral Stream Model using Genetic Programming. Applications of Evolutionary Computation, LNCS, vol. 7248, pp. 315–325 (2012) . https://link.springer.com/chapter/10.1007/978-3-642-29178-4_32
Cotta, C., Olague, G.: Resilient Bioinsired Algorithms: A Computer System Design Perspective. Applications of Evolutionary Computation, LNCS, vol. 13224, pp. 619–631 (2022). https://doi.org/10.1007/978-3-031-02462-7_39
Dozal, L., Olague, G., Clemente, E., Hernández, D.E.: Brain programming for the evolution of an artificial Dorzal stream. Cognit. Comput. 6, 528–557 (2014). https://doi.org/10.1007/s12559-014-9251-6
Flach, P.A., Kakas, A.C. (eds.): Abduction and Induction: Essays on their Relation and Integration. Applied Logic Series. Springer-Science+Business Media, B.V. (2000)
Fusing, H., Chen, C., Hsieh, Y.C., Farrell, P.: Lewis Carroll’s doublets net of English words: network heterogeneity in a complex system. PLoS One 9(12), e114177 (2014). https://doi.org/10.1371/journal.pone.0114177
Hernández, D.E., Clemente, E., Olague, G., Briseño, J.L.: Evolutionary multi-objective visual cortex for object classification in natural images. J. Comput. Sci. 17(Part 1), 216–233 (2016). https://doi.org/10.1016/j.jocs.2015.10.011
Hofman, M.A.: Chapter 18 - design principles of the human brain: an evolutionary perspective. Progr. Brain Res. 195, 373–390. https://doi.org/10.1016/B978-0-444-53860-4.00018-0
Ibarra-Vazquez, G., Olague, G., Chan-Ley, M., Puente, C., Soubervielle-Montalvo, C.: Brain programming is immune to adversarial attacks: towards accurate and robust image classification using symbolic learning. Swarm Evolut. Comput. 71, 101059, 17 pages (2022). https://doi.org/10.1016/j.swevo.2022.101059
Koza, J.R.: Genetic Programming: On the Programming of Computer by Means of Natural Selection. MIT Press, Cambridge (1992)
Koza, J.R.: Human-competitive results produced by genetic programming. Genet. Program. Evolv. Mach. 11, 251–284 (2010). https://doi.org/10.1007/s10710-010-9112-3
Luger, G.F.: Artificial Intelligence: Structures and Strategies for Complex Problem Solving. Addison-Wesley (2002)
Maynard-Smith, J.: Natural selection and the concept of a protein space. Nature 225, 563–564 (1970). https://www.nature.com/articles/225563a0.pdf
Mitchell, T.M.: Machine Learning. McGraw-Hill (1997)
Olague, G.: Evolutionary Computer Vision: The First Footprints. Springer (2016)
Olague, G., Clemente, E., Hernández, D.E., Barrera, A., Chan-Ley, M., Bakshi, S.: Artificial visual cortex and random search for object recognition. IEEE Access 7, 54054–54072 (2019). https://doi.org/10.1109/ACCESS.2019.2912792
Olague, G., Olague, M., Jacobo-Lopez, A.R., Ibarra-Vázquez, G.: Less is more: pursuing the visual turing test with the Kuleshov effect. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1553–1561 (2021). https://doi.org/10.1109/CVPRW53098.2021.00171
Olague, G., Menendez-Clavijo, J.A., Olague, M., Ocampo, A., Ibarra-Vázquez, G., Ochoa, R., Pineda, R.: Automated design of salient object detection algorithms with brain programming 35 pages (2022). arXiv:2204.03722v1. https://doi.org/10.48550/arXiv.2204.03722
O’Neill, M., Vanneschi, L., Gustafson, S., Banzhaf, W.: Open issues in genetic programming. Genet. Program. Evolv. Mach. 11, 339–363 (2010). https://doi.org/10.1007/s10710-010-9113-2
O’Neill, M., Spector, L.: Automatic programming: the open issue? Genet. Program. Evolv. Mach. 21, 251–262 (2020). https://doi.org/10.1007/s10710-019-09364-2
Rich, C., Waters, R.C.: Automatic programming: myths and prospects. Computer 21(8), 40–51 (1988). https://doi.org/10.1109/2.75
Rosenfeld, A.: Religion and the robot. Tradit: J. Orthodox Jewish Thought 8(3), 15–26 (1966). http://www.jstor.org/stable/23256081
Rusell, S., Norvig, P.: Artificial Intelligence a Modern Approach, 3rd edn. Prentice Hall (2010)
Salisbury, F.B.: Natural selection and the complexity of the gene. Nature 224, 342–343 (1969). https://www.nature.com/articles/224342a0.pdf
Samuel, A.L.: Some studies in machine learning using the game of checkers. IBM J. Res. Develop. 3(3), 210–229 (1959). https://doi.org/10.1147/rd.33.0210
Turing, A.M.: Computing machinery and intelligence. Mind LIX(236), 433-460 (1950). https://doi.org/10.1093/mind/LIX.236.433
Wittgenstein, L.: Tractatus Logico-Philosophicus, first English-language edition, Harcourt, Brace & Company, Inc (1922)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Olague, G. et al. (2023). Modeling Hierarchical Architectures with Genetic Programming and Neuroscience Knowledge for Image Classification Through Inferential Knowledge. In: Trujillo, L., Winkler, S.M., Silva, S., Banzhaf, W. (eds) Genetic Programming Theory and Practice XIX. Genetic and Evolutionary Computation. Springer, Singapore. https://doi.org/10.1007/978-981-19-8460-0_7
Download citation
DOI: https://doi.org/10.1007/978-981-19-8460-0_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8459-4
Online ISBN: 978-981-19-8460-0
eBook Packages: Computer ScienceComputer Science (R0)