Abstract
This paper is oriented to a computational theory of invariant perception by the cortex.
Based on the idea that the cortex has adopted representations and computational strategies that make the computation of invariants efficient, we suggest that in the cortex there are, at least, two paths for computing invariances. A path computes the parameters of invariance and the other applies them to original sensorial patterns. The neuronal structures that we propose in this paper uphold both the architecture and functionality of the cortex.
We present a model of neural net which computes the homothetic parameter of an one-dimensional tonotopic pattern. This theoretical problem has, as substratum, the spatially layered architecture of Primary Auditory Cortex, (AI), and the associated computational concepts. The neuronal synthesis of the model is achieved combining McCulloch-Pitts and analytical formulations, which allows us to obtain a neural layered computing structure.
In addition, we propose an alternative net for computing invariances which is derived from methods of artificial systems visual processing. These neural structures, when working in two-dimensional spaces, allow reaching, in a natural way, a complete schema of recognition for artificial visual systems.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Suárez Araujo, C.P. (1990): “Contribuciones a la Integratión Multisensorial y Computación Neuronal Paralela. Aplicaciones”. Doctoral Thesis. University of Las Palmas de Gran Canaria.
Suárez Araujo, C.P. and Moreno-Díaz, R. (1987): “Modelo para una Computación Neuronal de Invarianzas Auditivas”. In Proc. of III Int. Symp. Biomed. pp. 689–694. Madrid (Spain).
Moreno-Díaz, R.; Mira Mira, J.; Suárez Araujo, C.P. and Delgado, A. (1989): “Neuronal Net to Compute Homothetic Auditive Invariances”. In Proc. V. Medit. Conference on Medical and Biol. Engi. Patras (Greece).
Mira Mira, J. and Moreno-Díaz, R. (1982): “Un Marco Teórico para Interpretar la Función Neuronal a Altos Niveles”. In Proc. I. Reunión Nac. Biocibernética. Real Academia de Ciencias. pp. 151–157.
Pitts. W. and McCulloch, W. (1947): “How we Know Universals. The Perception of Auditory and Visual Forms”. Bull. Math. Biophys. 9, pp. 127–147.
Arbib, M.A. (1987): “Brain, Machines, and Mathematics”. Springer-Verlag.
Ballard, D.H. (1987): “Cortical Connections and Parallel Processing: Structure and Function”. In Vision, Brain, and Cooperative Computation. Eds: Arbib, M. and Hanson, A. M.I.T. Press.
Treuhb, A. (1987): “Visual-Cognitive Neuronal Networks”. In Vision, Brain, and Cooperative Computation. Eds: Arbib, M. and Hanson, A. M.I.T. Press.
Marr, D. and Hildreth. (1980): “Theory of Edge Detection”. In Proc. R. Soc. Lond., B 207, pp. 187–217.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Suárez Araujo, C.P., Moreno-Díaz, R. (1992). Neural structures to compute homothetic invariances for artificial perception systems. In: Pichler, F., Díaz, R.M. (eds) Computer Aided Systems Theory — EUROCAST '91. EUROCAST 1991. Lecture Notes in Computer Science, vol 585. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0021040
Download citation
DOI: https://doi.org/10.1007/BFb0021040
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55354-0
Online ISBN: 978-3-540-47034-2
eBook Packages: Springer Book Archive