Abstract
It is our deep feeling that Computational Neuroscience and Connectionist Engineering are in stagnancy and some fresh air is needed. The purpose of this paper is to contribute to the description of the possible causes of this blockage: lack of a new mathematics for plasticity, fault tolerance, cooperative processes, and abstraction mechanisms to link the physical level to the cognitive processes. Also is clear that we have much more data than contributions to a realistic theory of the brain. As engineering we find again the lack of methodology, serious limitations of the formal model underlying all the ANN paradigms and the necessity to end with the old rivalry between the symbolic and connectionist perspectives of AI.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Arbib, M. (ed.): The Handbook of Brain Theory and Neural Networks. The MIT Press, Cambridge, MA (1995)
Feynman, R.P., Leighton, R.B., Sands, M.: The Feynman Lectures on Physics. Addison-Wesley, Reading, Mass (1966)
Haykin, S.: Neural Networks: A Comprehensive Foundation, Prentice-Hall. (1999)
Hillario, M., M., Llamement, Y. and Alexandre, F.: Neurosymbolic integration: Unified versus hybrid approaches. The European Symposium on Artificial Neural Networks. Brussels, Belgium (1995)
Marr, D.: (1982) Vision. Freeman, New York
Mira, J. and Delgado, A.E.: Where is knowledge in robotics? Some methodological issues on symbolic and connectionist perspectives of AI. In Ch. Zhou, D. Maravall and Da Rua (eds.) Autonomous Robotic Systems. Ch. I. Physica-Verlag. Springer-Verlag (2003) 3–34
Mira, J., Delgado, A.E.: A Logical Model of Co-Operative Processes in Cerebral Dynamics. Cybernetics and Systems, An International Journal, 18: (1987) 319–349
Mira, J., Delgado, A.E.: Neural Modeling in Cerebral Dynamics. Mathematical Biosciences. Special number ed. by L. Ricciardi, 2003 (pend. pub.)
Mira, J., Delgado, A.E., Taboada, M.J.: Neurosymbolic Integration: The Knowledge Level Approach. R. Moreno-Diaz et al (eds) Cast and Tools for Complexity in Biological, Physical and Engineering Systems. Extended Abstracts of EUROCAST (2003)
Mira, J., Prieto, A. (eds.): Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. LNCS 2084, Springer Verlag (2001)
Newell, A.: The knowledge level. AI Magazine, summer 1–2 (1981)
Schreiber, et al.: Engineering and managing knowledge: The CommonKADS methodology. The MIT Press (1999)
Schwartz, E.L. (ed.): Computational Neuroscience. MIT Press (1990)
Sun, R., Alexandre, F Sun, (eds.): Connectionist-Symbolic Integration. Lea. London (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mira, J.M. (2003). Real Neurons and Neural Computation: A Summary of Thoughts. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_3
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive