Results 1 
7 of
7
An Exact and Direct Analytical Method for the Design of Optimally Robust CNN Templates
 IEEE TRANS. CIRCUITS & SYST.I
, 1999
"... In this paper, we present an analytical design approach for the class of bipolar cellular neural networks (CNN's) which yields optimally robust template parameters. We give a rigorous definition of absolute and relative robustness and show that all welldefined CNN tasks are characterized by a finit ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
In this paper, we present an analytical design approach for the class of bipolar cellular neural networks (CNN's) which yields optimally robust template parameters. We give a rigorous definition of absolute and relative robustness and show that all welldefined CNN tasks are characterized by a finite set of linear and homogeneous inequalities. This system of inequalities can be analytically solved for the most robust template by simple matrix algebra. For the relative robustness of a task, a theoretical upper bound exists and is easily derived, whereas the absolute robustness can be arbitrarily increased by template scaling. A series of examples demonstrates the simplicity and broad applicability of the proposed method.
The freenet homepage. http://freenet.sourceforge.net
 IEEE Transactions on Circuits and Systems I
, 1998
"... Abstract—Morphology provides the algebraic means to specify operations on images. Discretetime cellular neural networks (DTCNN’s) mechanize the execution of operations on images. The paper first shows the equivalence between morphological functions and DTCNN’s. Then, the argument is extended to t ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Abstract—Morphology provides the algebraic means to specify operations on images. Discretetime cellular neural networks (DTCNN’s) mechanize the execution of operations on images. The paper first shows the equivalence between morphological functions and DTCNN’s. Then, the argument is extended to the synthesis of optimal DTCNN structures from complex morphological expressions. It is shown that morphological specifications may be freely derived, to be subsequently transformed and adopted to the needs of a specific target technology. This process of technology mapping can be automated along the welltrodden path in CAD for microelectronics. I.
Article A Novel Cloning Template Designing Method by Using an Artificial Bee Colony Algorithm for Edge Detection of CNN Based Imaging Sensors
, 2011
"... sensors ..."
An Analysis of CNN Settling Time
, 1998
"... The settling time of cellular neural networks (CNNs) is crucial for both simulation and applications of VLSI CNN chips. The computational effort for the numerical integration may be drastically reduced, and CNN programs can be optimized, if a priori knowledge on the settling time is available. Moreo ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The settling time of cellular neural networks (CNNs) is crucial for both simulation and applications of VLSI CNN chips. The computational effort for the numerical integration may be drastically reduced, and CNN programs can be optimized, if a priori knowledge on the settling time is available. Moreover, this allows the parameters necessary to achieve higher processing speed to be tuned. For certain template classes, we present analytic solutions, while for others, tight upper bounds are given. 1. INTRODUCTION In this paper, we consider the class of singlelayer, spatially invariant cellular neural networks (CNNs) with neighborhood radius one, following the definition given in [1]. The dynamics of the network is governed by a system of n = MNdifferential equations, d x i (t) d t =x i (t) + X k#N i a k f (x k (t)) +b k u k + I + # i ,(1) where N i denotes the neighborhood of the cell C i , a k and b k the template parameters, and # i the contribution from the boundar...
Optimization of CNN Template Robustness
, 1999
"... Introduction 1.1 The Classo Bip Cellular Neural Netwo0A In this letter, weco00b the classo singlelayer, spatially invariant cellular neural netwo05 (CNNs) with neighbogho d radiusodi foiu wing thedefinitio given in [1]. The dynamicso the netwo isgo verned by a systemo MN di#erentialequatio5b ..."
Abstract
 Add to MetaCart
Introduction 1.1 The Classo Bip Cellular Neural Netwo0A In this letter, weco00b the classo singlelayer, spatially invariant cellular neural netwo05 (CNNs) with neighbogho d radiusodi foiu wing thedefinitio given in [1]. The dynamicso the netwo isgo verned by a systemo MN di#erentialequatio5b dx i (t) dt = x i (t)+ # k#N i # a k f(x k (t)) + b k u k # + I (1) where N idenob the neighoig o d o the cell C i , A = {a k } and B = {b k } the feed ack and co tro template parameters, respectively. f() is
Counterexample of a Claim Pertaining to the Synthesis of a Recurrent Neural Network
"... Recurrent Neural Networks has received much attention due to its nonlinear dynamic behavior. One such type of dynamic behavior is that of setting to a fixed stable state. ..."
Abstract
 Add to MetaCart
Recurrent Neural Networks has received much attention due to its nonlinear dynamic behavior. One such type of dynamic behavior is that of setting to a fixed stable state.
SineCosineTaylorLike Method for HoleFiller ICNN Simulation
"... SineCosineTaylorLike method is employed to improve the performance of image or handwritten character recognition under improved cellular nonlinear network environment. The ultimate aim of this paper is focused on developing an efficient design strategy for simulating hole filler under ICNN array ..."
Abstract
 Add to MetaCart
SineCosineTaylorLike method is employed to improve the performance of image or handwritten character recognition under improved cellular nonlinear network environment. The ultimate aim of this paper is focused on developing an efficient design strategy for simulating hole filler under ICNN arrays with a set of inequalities satisfying its output characteristics by considering the parameter range.