By Topic

ASIM, an efficient simulation environment for cellular neural networks and analog arrays

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
K. R. Krieg ; Dept. of Electr. Eng., California Univ., Berkeley, CA, USA ; L. O. Chua

Summary form only given. Traditional circuit-based simulation of cellular neural networks and analog arrays is very slow and cumbersome. Much of the computation and memory space involved could be reduced if the data and computational structures of the program could mirror the architecture of the analog array. The authors present the details of such a simulator, named ASIM. The computations performed by ASIM are derived directly from the nonlinear differential equations describing the processing at each node and the internal data representation mirrors the architecture of analog arrays. ASIM is a graphical environment for simulating continuous-time continuous-variable computational arrays which have a regular structure, whose connectivity is nearest-neighbor, and whose nodal processing can be described by a set of nonlinear differential equations. The user need specify only the equations for nodal processing and the connectivity to neighboring processors. Input and output are graphical and show the state of all variables in the array as a function of time. The user may incorporate iteration of any internal variable to find optimal processing strategies or neighborhood organization. To aid the evaluation of algorithms which are to be fabricated in VLSI, the use can specify variances in any computational variable to simulate the effect of fabrication tolerances and may specify that certain variables have associated noise components. Both of these features make ASIM an ideal aid in developing analog array and cellular neural network algorithms which are more robust to implementation variability. The ASIM program runs on 80386 based IBM PC/AT computers using the MS-DOS operating system. It requires 2 Mbytes of extended memory and a VGA compatible graphics card

Published in:

Cellular Neural Networks and their Applications, 1990. CNNA-90 Proceedings., 1990 IEEE International Workshop on

Date of Conference:

16-19 Dec 1990