This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Software Environment for Studying Computational Neural Systems
July 1992 (vol. 18 no. 7)
pp. 575-589

UCLA-SFINX is a neural network simulation environment that enables users to simulate a wide variety of neural network models at various levels of abstraction. A network specification language enables users to construct arbitrary network structures. Small, structurally irregular networks can be modeled by explicitly defining each neuron and can be modeled by explicitly defining each neuron and corresponding connections. Very large networks with regular connectivity patterns can be implicitly specified using array constructs. Graphics support, based on X Windows System, is provided to visualize simulation results. Details of the simulation environment are described, and simulation examples are presented to demonstrate SFINX's capabilities.

[1] L. D. Harmon and E. R. Lewis, "Neural modeling,"Physiological Review, vol. 46, pp. 513-591, 1966.
[2] H. F. Bradford,Chemical Neurobiology: An Introduction to Neurochemistry, New York: Freeman, 1986.
[3] B. Katz and R. Miledi, "A study of spontaneous miniature potentials in spinal motoneurons,"J. Physiology (London), vol. 168, pp. 389-422, 1963.
[4] W. Rall, "Core conductor theory and cable properties of neurons," inHandbook of Physiology, Vol. 1: The Nervous System. Bethesda, MD: American Physiological Society, 1977, pp. 39-98.
[5] D. E. Rumelhartet al., "Learning internal representations by error propagation,Tech. Rep. 8506, Institute For Cognitive Science, Univ. California, San Diego, 1985.
[6] T. Kohonen,Self-Organization and Associative Memory. Berlin, Germany: Springer-Verlag, 1988, p. 132.
[7] K. Fukushima, "Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,"Bio. Cybern., vol. 36, pp. 193-202, 1980.
[8] E. Paiket al., "UCLA SFINX--A neural network simulation environment," inProc. IEEE First Annual Int. Conf. Neural Networks, pp. 367-376, June 1987.
[9] E. Mesrobianet al., "UCLA SFINX--Structure and function in neural Connections,"Tech. Rep. UCLA-MPL-TR 89-8, Machine Perception Laboratory, Univ. California, Los Angeles, Nov. 1989.
[10] E. Mesrobian and J. Skrzypek, "Discrimination of natural textures: A neural network architecture," inProc. IEEE First Annual Int. Conf. Neural Networks, pp. 247-258, June 1987.
[11] I. Heisey and J. Skrzypek, "Color constancy and early vision: A connectionist model," inProc. IEEE First Annual Int. Conf. Neural Networks, pp. 317-325, June 1987.
[12] J. Skrzypek, "Lightness constancy: Connectionist architecture for controlling sensitivity,"IEEE Trans. Syst., Man, Cybern., vol. 20, pp. 957-968, Sept./Oct. 1990.
[13] J. Skrzypek and J. Hoffman, "Visual recognition of script characters and neural network architectures," inNeural Networks: Advances and Applications, E. Gelenbe, Ed. Elsevier Science Publishers, 1991, pp. 109-144.
[14] B. Ringer and J. Skrzypek, "A neural architecture for illusory contour detection,"Tech. Rep. UCLA-MPL-TR 91-8, Machine Perception Laboratory, Univ. California, Los Angeles, 1991.
[15] J. Skrzypeket al., "Neural networks for recognition of handwritten script characters: Comparative analysis," inFrontiers on Handwriting Recognition, C. Impedovo, Ed. New York: Springer-Verlag, 1991.
[16] D. Gungner and J. Skrzypek, "UCLA PUNNS--A neural network machine for computer vision," inProc. SPIE Conf. Image Understanding and the Man-Machine Interface, 1987.
[17] J. K. Ousterhout, "Tcl: An embeddable command language," inProc. 1990 Winter USENIX Conf., pp. 133-146, 1990.
[18] D. Rose, "Mechanisms underlying the receptive field properties of neurons in cat visual cortex,"Vision Research, vol. 19, pp. 533-544, 1979.
[19] S. Marcelja, "Mathematical description of the responses of simple cortical cells,"J. Optical Society America, vol. 70, pp. 1297-1300, 1980.
[20] J. D. Daugman, "Two-dimensional spectral analysis of cortical receptive field profiles,"Vision Research, vol. 20, pp. 847-856, 1980.
[21] M. J. Hawken and A. J. Parker, "Spatial properties of neurons in the monkey striate cortex,"Proc. Royal Society London, Series B, vol. 231, pp. 251-288, 1987.
[22] R. A. Young, "The Gaussian derivative model for machine vision: Visual cortex simulation,Tech. Rep. GMR-5323, General Motors Research Laboratories, 1986.
[23] J. A. Marshall, "Represention of uncertainty in self-organizing neural networks,"Tech. Rep., Center for Research in Learning, Perception, and Cognition and Minnesota Supercomputer Institute, Apr. 1990.
[24] D. H. Perkel, "A computer program for simulating a network of interacting neurons,"Computers and Biomedical Research, vol. 9, pp. 31-43, 1976.
[25] L. D. Wittie, "Large-scale simulation of brain corticies,"Simulation, vol. 31, Sept. 1978.
[26] M. A. Wilsonet al., "GENESIS: A system for simulating neural networks," inAdvances in Neural Information Processing Systems I, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1989.
[27] B. Katz,Nerve, Muscle, and Synapse, New York: McGraw-Hill, 1966.
[28] N. H. Goddardet al., "Rochester connectionist simulator,"Tech. Rep. TR 233(revised), Dept. Computer Science, Univ. Rochester, Oct. 1989.
[29] C. L. D'Autrechyet al., "A general-purpose simulation environment for developing connectionist models,"Simulation, vol. 51, July 1988.
[30] A. Wieland and R. Leighton, "The Asprin/MIGRANES software tools," inProc. NIPS'89, IEEE Conf. Neural Information Processing Systems Natural and Synthetic, Nov. 1989.
[31] D. Wang and C. Hsu, "SLONN: A simulation language for modeling of neural networks,"Simulation, vol. 55, Aug. 1990.
[32] M. Kranzdorf, Mactivation User'sManual Version 3.3, 1990. (The author can be reached via email -mikek@boulder.colorado.edu.)
[33] S. Coghlanet al., "A computer simulation system for building models of neurobiological networks," inProc. Workshop on Analysis and Modeling of Neural Systems 1990, July 1990.
[34] J. W. Tromp and F. H. Eeckman, "An approach to realistic simulation and its application to the olfactory bulb," inProc. Workshop on Analysis and Modeling of Neural Systems 1990, July 1990.

Index Terms:
graphics supports; software environment; computational neural systems; UCLA-SFINX; simulation environment; network specification language; arbitrary network structures; array constructs; X Windows System; digital simulation; formal specification; neural nets; programming environments; specification languages
Citation:
E. Mesrobian, J. Skrzypek, "A Software Environment for Studying Computational Neural Systems," IEEE Transactions on Software Engineering, vol. 18, no. 7, pp. 575-589, July 1992, doi:10.1109/32.148476
Usage of this product signifies your acceptance of the Terms of Use.