Abstract
This paper proposes a model of perception that allows animals to classify objects in the environment. We consider the transformation of semantic information in the four blocks of the model that imitate the mechanism of operation of sensory systems. Receptors convert external influences into stimuli that are transformed into sensations in accordance with the law of requisite variety via the data randomizing. Perception is formed by the generalization of all sensations, as well as the corresponding information accumulated by the animal. To find appropriate prototypes of objects forming classes, there is a compression of the processed information. This process is modeled via the creation of granules containing objects with close values for every feature. Granulation allows us to find the most probable class of the object corresponding to the average frequency value of its features. Algorithms for object classification on basis of the model and the invariant paradigm are identical and posses the simplicity and versatility at a high accuracy of the solution.
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
References
Red’ko, V.G.: Evolution, neural networks, intelligence: models and concepts of evolutionary cybernetics, p. 220. URSS, Moscow (2015)
Pokrovsky, V.M., Korotko, G.F.: (eds.) Human physiology. In: Medicine, vol. 2, p. 368 (1997)
Smith, C.U.M.: Biology of Sensory Systems, p. 583. Aston University, Birmingham (2009)
Loskutov, A., Mikhaylov, A.S.: Fundamentals of the theory of complex systems, p. 620. Institute of Computer Studies, Moskow (2007)
Solso, R.: Cognitive Psychology, 6th edn, p. 589. Allyn and Bacon, Boston (2006)
Bratus, B.S.: General psychology. In: Gusev, A.N. (ed.) Sensation and Perception, vol. 2, p. 416. Academy, Moscow (2007)
Feynman, R.: The character of physical law. A series of lectures recorded by the BBC at Cornell University USA. Cox and Wyman, London (1965)
Zadeh, L.: Fuzzy sets and information granularity. In: Gupta, N., Ragadem, R., Yager, R. (eds.) Advances in Fuzzy Set Theory and Applications, pp. 3–18. North-Holland, Amsterdam (1979)
Ashby, W.R.: An Introduction to Cybernetics, 2nd edn, p. 295. Chapman and Hall, London (1957)
Granichin, O.N., Polyak, B.T.: Randomized Algorithms of an Estimation and Optimization Under Almost Arbitrary Noises, p. 209. Nauka, Moscow (2003)
Shats, V. N.: On new computing technology in machine learning. In: 17th Proceeding International Conference Neuroinformatics, vol. 2, pp. 148–158. MEPhI, Moskow (2015)
Shats, V.N.: Invariants of matrix data in the classification problem. Stochastic Optimization Informatics. 12(2), 17–32 (2016). SPbGU, St. Petersburg http://www.math.spbu.ru/user/gran/optstoch.htm
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Shats, V.N. (2018). The Classification of Objects Based on a Model of Perception. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research. NEUROINFORMATICS 2017. Studies in Computational Intelligence, vol 736. Springer, Cham. https://doi.org/10.1007/978-3-319-66604-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-66604-4_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66603-7
Online ISBN: 978-3-319-66604-4
eBook Packages: EngineeringEngineering (R0)