Comprehensive functional testing and dynamic compensation techniques for Cellular Neural Networks /

additional hardware, and are limited to specific topologies. The

Bibliographic Details
Main Author: Grimaila, Michael Russell
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1995.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:additional hardware, and are limited to specific topologies. The
and system offsets. Whenever possible, the compensation
arrays independent of the size or topology of the array. The
Cellular Neural Networks (CNN's) are analog, non-linear, dynamic
characterize and attempt to minimize or eliminate the effect
conduct functional testing and dynamic compensation of CNN
different complexities, combine input stimulus files in a
fabricated in sub-micron Very Large Scale Integration (VLSI)
functionality of CNN'S. Present techniques for testing CNN
goal of this thesis is to provide a deterministic method to
hardware provide only limited capabilities, often require
in real CNN hardware. The functional tests consist of a
independently, otherwise a global compensation approach is
logical manner, and generate the necessary files for
methods provide comprehensive, non-invasive techniques for
mismatches, non-linearity in the multipliers and state nodes,
need to develop robust testing methods to establish baseline
of software tools was developed to select CNN macromodels of
of undesirable parametric faults such as time-constant
output vector set. The dynamic compensation strategies
propagated to the output where it is compared to a known good
provide insight into different problems faced when testing a
refine, and measure the effectiveness of the proposed testing
sequence of inputs to the array that insure each node in the
simulation. The simulation results were used to design,
strategies.
system level representation of the CNN is toggled and
systems which are especially well suited for solving problems in
techniques are carried out locally on each cell
technologies. The increase in circuit integration has driven the
the areas of image processing and pattern recognition. State of
the art implementations of two-dimensional CNN's arrays are
used. Numerous CNN architectures had to be modeled to
verifying the integrity of each of the functional paths as
VLSI implementations of CNN arrays. For this reason, a set
well as procedures to measure and minimize parametric faults
Item Description:"Major subject: Electrical Engineering".
Vita.
Physical Description:xiv, 127 leaves : illustrations ; 28 cm.
Also available online.
Issued also on microfiche from Lange Micrographics.
Bibliography:Includes bibliographical references.