Current interest in neural networks has produced a diverse set of algorithms and architectures that vary in connectivity pattern, temporal behavior, update rules, and convergence properties. We have designed a flexible simulation system that can support the implementation of a wide range of neural network approaches. The UCLA-SFINX simulator is especially suited for the exploration of structured, irregular, and layered connectivity patterns. Func tions, such as those in early vision, are modeled using the regular connectivity of center/surround antagonistic receptive fields and can be implemented as the difference of concentric gaussians. Higher level cognitive functions, such as supervised and unsuper vised learning, have more irregular, dynamic connectivity structures and update mechanisms that are also supported. To visualize weight spaces, input/output training sets, image data, or other network characteristics, SFINX provides an X- windows based graphical output that assists in rapidly assessing the consequences of altering connectivity patterns, parameter tuning, and other experiments.
J. Skrzypek, E. Mesrobian, and D. Gungner.Neural Networks for Computer vision: A framework for specification of a general purpose vision system. In Proceedings of SPIE Conference on Image Understanding and the Man-Machine Interface, Los Angeles, California, January 1989.
2.
L.D. Harmon and E.R. Lewis.Neural modeling. Physiological Review, 46:513-591,1966.
3.
H.F. Bradford.Chemical Neurobiology: An Introduction to Neurochemistry. Freeman, New York, 1986 .
4.
B. Katz and R. Miledi.A study of spontaneous miniature potentials in spinal motoneurons . Journal of Physiology ( London), 168(3):389-422,1963.
5.
W. Rall.Core conductor theory and cable properties of neurons. In Handbook of Physiology, Vol. 1: The Nervous System, pages 39-98, American Physiological Society, Bethesda, Md.1977.
6.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams.Learning Internal Representations By Error Propagation . Technical Report ICS Report 8506, Institute For Cognitive Science, University of California, San Diego, 1985.
7.
T. Kohonen.Self-Organization and Associative Memory. Springer-Verlag , New York, 1984.
8.
K. Fukushima .Neocognitron: A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position . Biological Cybernetics, 36:193-202, 1980.
9.
E. Paik, D. Gungner, and J. Skrzypek.UCLA SFINX - A neural network simulation environment . In Proceedings of the IEEE First Annual International Conference on Neural Networks, pages 367-376, San Diego, California , June 1987.
10.
E. Mesrobian , M. Stiber, and J. Skrzypek.UCLA SFINX — Structure and Function in Neural Connections. Technical Report UCLA-MPL-TR 89-8, Machine Perception Laboratory, University of California , Los Angeles, November 1989.
11.
E. Mesrobian and J. Skrzypek.A Neural Architecture for Textural Segmentation . In Proceedings of the Third Annual Parallel Processing Symposium, Fullerton, California , March 1989.
12.
I. Heisey and J. Skrzypek.Color constancy and early vision: A connectionist model . In Proceedings of the IEEE First Annual International Conference on Neural Networks, pages 317-325, San Diego, California , June 1987.
13.
J. Skrzypek .Lightness constancy: connectionist architecture for controlling sensitivity. To appear in IEEE SMC, 1991.
14.
J.L. McClellandD.E. Rumelhart and the PDP Research Group. Parallel Distributed Processing. MIT Press, Cambridge, Mass., 1986 .
15.
J. A. Anderson and E. Rosenfeld , editors. NEUROCOMPUTING: Foundations of Research. MIT Press, Cambridge, Massachusetts, 1988.
16.
B.D. Shriver .Artificial Neural Systems. IEEE Computer, 21(3):8-9, March 1988.
17.
W.S. McCulloch and W. Pitts.A logical calculus of the ideas imminent in nervous activity. Bulletin of Mathematical Biophysics , 5:115-133,1943.
18.
N. Rochester , J.H. Holland, L.W. Haibt, and W.L. Duda.Tests on a cell assembly theory of the action of the brain, using a large digital computer . IRE Transactions on Information Theory, TT-2:80-93,1956.
19.
F. Rosenblatt .The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review , 65:386-408,1958.
20.
F. Rosenblatt .Principles of Neurodynamics. Spartan, New York,1962.
21.
D.O.Hebb.The Organization of Behavior. John Wiley and Sons , New York, 1949.
22.
B. Widrow and M.E. Hoff.Adaptive switching circuits. 1960WESCON Convention Record, Part IV:96-104,1960.
23.
P. Werbos.Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD thesis, Harvard University Committee on Applied Mathematics, Cambridge, Mass. , 1974.
24.
D. Gungner and J. Skrzypek.UCLA PUNNS - A neural network machine for computer vision . In Proceedings of SPIE Conference on Image Understanding and the Man-Machine Interface, 1987.
25.
D.H. Perkel .A Computer Program for Simulating a Network of Interacting Neurons. Computers and Biomedical Research , 9:31-43,1976.
26.
L.D. Wittie .Large-scale Simulation of Brain Corticies . SIMULATION, 31(3), September 1978.
27.
M.A. Wilson , U.S. Bhalla, J.D. Uhley, and J.M. Bower.GENESIS: A system for simulating neural networks. In D. S. Touretzky , editor, Advances in Neural Information Processing Systems I, Morgan Kaufmann Publishers, San Mateo, California, 1989. Collected papers of the IEEE Conference on Neural Information Processing Systems — Natural and Synthetic, Denver, Colorado, November 1988.
28.
B. Katz.Nerve, muscle, and synapse. McGraw-Hill, Inc., New York, 1966.
29.
N.H. Goddard , K.J. Lynne, T. Mintz, and L. Bukys.Rochester Connectionist Simulator. Technical Report TR 233 (revised), Department of Computer Science, University of Rochester, October 1989 .
30.
C.L. D'Autrechy , J.A. Reggia, G.C. Sutton, III, and S.M. Goodall.A general-purpose simulation environment for developing connectionist models . SIMULATION, 51 (1 ), July 1988.
31.
A. Wieland and R. Leighton.The Asprin/MIGRANES Software Tools. In Proceedings of NIPS'89 , IEEE Conference on Neural Information Processing Systems - Natural and Synthetic, Denver, Colorado , November 1989.
32.
D. Wang and C. Hsu.SLONN: A Simulation Language for modeling Of Neural Networks . SIMULATION, 55(2), August 1990.
33.
M. Kranzdorf .Mactivation User's Manual Version 3.3. 1990. The author can be reached via email- mikek@boulder.colorado.edu.
34.
S. Coghlan , M.V. Gremillion, and B. Travis.A Computer Simulation System for Building Models of Neurobiological Networks. In Proceedings of the Workshop on Analysis and Modeling of Neural Systems1990, Berkeley, California, July 1990.
35.
J.W. Tromp and F.H. Eeckman.An Approach to Realistic Simulation and its Application to the Olfactory Bulb. In Proceedings of the Workshop on Analysis and Modeling of Neural Systems1990, Berkeley, California, July 1990 .
36.
S.W. Kuffler , J.G. Nicholls, and A.R. Martin.From Neuron to Brain . Sinauer Associates Inc., Sunderland, Massachusetts, second edition, 1984.
