Last ned (Gratis)

Abstrakt

SEVANN is a script-based approach to enhancing
the general process of evolving artificial neural networks
(ANNs), particularly the more biologically-plausible models.
It employs a relatively standard dissection and classification
of network components to facilitate modular ANN design
and scripting; it then uses the scripts to govern both the
formulation of genotypes and their conversion to phenotype
ANNs. The use of genetic variables in scripts allows the
user to test different combinations of hard-wired and evolved
parameters during an interactive design process, without any
additional coding or compiling.

Referanser

[1] B. Aisa, B. Mingus, and R. O’Reilly. The emergent neural
modeling system. Neural Networks, 20(8):1146–1152, 2008.


[2] J. Bower and D. Beeman. The Book of GENESIS; Exploring
General Neural Models with the GEneral NEural Simulation
System. Springer-Verlag, New York, 2 edition, 1998.


[3] R. Callan. The Essence of Neural Networks. Prentice Hall,
London, England, 1999.


[4] N. Carnevale and M. Hines. The NEURON Book. Cambridge
University Press, Cambridge, UK, 2006.


[5] P. Dayan and L. Abbott. Theoretical Neuroscience: Computational
and Mathematical Modeling of Neural Systems. The MIT
Press, Cambridge, MA, 2001.


[6] K. L. Downing. Development and the Baldwin effect. Artificial
Life, 10(1):39–63, 2004.


[7] Y. Fregnac. Hebbian synaptic plasticity. In M. Arbib, editor, The
Handbook of Brain Theory and Neural Networks, pages 515–522.
The MIT Press, Cambridge, MA, 2003.


[8] S. Haykin. Neural Networks: A Comprehensive Foundation.
Prentice Hall, Inc., Upper Saddle River, N.J., 1999.


[9] D. Hebb. The Organization of Behavior. John Wiley and Sons,
New York, NY, 1949.


[10] J. Hopfield. Neural networks and physical systems with
emergent collective computational abilities. Proceedings of the
National Academy of Sciences, 79:2554–2558, 1982.


[11] T. Kohonen. Self-Organizing Maps. Springer, Berlin, 2001.


[12] J. LeDoux. Synaptic Self: How Our Brains Become Who We Are.
Penguin Books, Middlesex, England, 2002.


[13] B. McNaughton, L. Battaglia, O. Jensen, E. I. Moser, and M. B.
Moser. Path integration and the neural basis of the ’cognitive
map’. Nature Reviews Neuroscience, 7(8):663–678, 2006.


[14] R. C. O’Reilly and Y. Munakata. Computational Explorations
in Cognitive Neuroscience. The MIT Press, Cambridge, Massachusetts,
2000.
[15] R. S. Sutton and A. G. Barto. Reinforcement Learning: An
Introduction. MIT Press, Cambridge, MA, 1998.


[16] P. Turney, L. D. Whitley, and R. W. Anderson. Introduction to
the special issue: Evolution, learning, and instinct: 100 years
of the Baldwin effect. Evolutionary Computation, 4(3):iv–viii,
1997.


[17] B. Weber and D. Depew, editors. Evolution and Learning: The
Baldwin Effect Reconsidered. The MIT Press, Cambridge, MA,
2003.


[18] L. Yaeger. Computational genetics, physiology, metabolism,
neural systems, learning, vision and behavior or polyworld:
Life in a new context. In C. G. Langton, editor, Artificial
Life III, Proceedings Volume XVII, pages 263–298, Reading,
Massachusetts, 1994. Santa Fe Institute Studies in the Sciences
of Complexity, Addison-Wesley.


[19] X. Yao. Evolving artificial neural networks. Proceedings of the
IEEE, 87(9):1423–1447, 1999.








Forrige artikkel      Neste artikkel