Abstract
Linear and non-linear local computation with self-programming facilities is the more used model of biological neural nets. The diversity, specificity and complexity of anatomo-physiological contacts (dendrite-dendrite, axon-axon, axon-dendrite,...) and the variety of local processes carried out by those contacts make one think of authentic subcellular microcomputation.
To illustrate the enormous computational capacity asociated to a neuron we present the masks necessary to solve the more usual equations of classical physics (Newton, Diffusion,...) and compare with the dendritic field of a Purkinje cell.
Size, form and symmetries in the anatomy of receptive fields are interpreted as responsable of specific spatio-temporal filtering, orientation and movement detection. Furthermore, there is experimental evidence of other algorithmic local functions which do not have an analytical counterpart and consequently are not considered in this paper.
Preview
Unable to display preview. Download preview PDF.
References
T.H. Bullock, R. Orkand and A. Grinnell. Introduction to Nervous Systems. W.H. Freeman and Company. San Francisco. (1977).
L.O. Chua, L. Yang and K.R. Krieg: Signal Processing Using Cellular Neural Network. Journal of VLSI Signal Processing 3, pp. 25–51. Kluwer Academic Publishers. Boston. (1991).
D.F. Forbus: Qualitative Process Theory. Artificial Intelligence, 24. pp. 85–168. (1984)
B. Kuiper: Qualitative Simulation. Artificial Intelligence, 29. pp. 289–388. (1986)
J.Y. Lettvin et al.: What the Frog's Eye Tells the Frog's Brain. Proceedings of the IRE. Vol. 47, No. 11, pp. 1940–1959. (1959).
W.S. McCulloch and Pitts: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, Vol. 5, pp. 115–133. Chicago Univ. Press. (1943).
W.S. McCulloch: Embodiments of mind”. The MIT Press. Mass. (1965).
J. Mira and A.E. Delgado: Linear and Algorithmic Formulation of Cooperative Computation in Neural Nets. In F. Pichler, R. Moreno Díaz (eds): Computer Aided Systems Theory. Lecture Notes in Computer Science, 585. Berlin: Springer 1992, pp. 2–20.
J. Mira et al: Towards More Realistic Self-contained Models of Neurons: High-order, Recurrence and Local Learning. In J. Mira et al (eds): New Trend in Neural Computation. Lecture Notes in Computer Science, 686. Berlin: Springer 1993, pp. 55–62.
R. Moreno Díaz: Deterministic and probabilistic neural nets with loops. Mathematical Biosciences 11, pp. 129–136. (1971).
R. Moreno Díaz y F. Martín Rubio: Incidencia de la Informática en la Educación. Radio y Educación de Adultos. n∘ 6. pp. 5–8. Las Palmas de G.C. España. (1987)
D.E. Rumelhart, G.E. Hinton and R.J. Williams: Learning Internal Representations by Error Propagation. In D.E. Rumelhart and McClelland and the PDP Research Group (eds): Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations. The MIT Press. Mass, 1986.
F.O. Schmitt and F.G. Worden: The Neuroscience Fourth Study Program. The MIT Press. Mass. (1979).
D.S. Weld and J. de Kleer (eds): Reading in Qualitative Reasoning and Physical Systems. Morgan Kaufmann Pub. San Mateo. Californa. USA (1990).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Delgado, A., Moreno-Díaz, R., Mira, J. (1994). Qualitative computation with neural nets: Differential equations like examples. In: Pichler, F., Moreno Díaz, R. (eds) Computer Aided Systems Theory — EUROCAST '93. EUROCAST 1993. Lecture Notes in Computer Science, vol 763. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57601-0_63
Download citation
DOI: https://doi.org/10.1007/3-540-57601-0_63
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57601-3
Online ISBN: 978-3-540-48286-4
eBook Packages: Springer Book Archive