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 ..."
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.
On the Complexity of Image Processing and Pattern Recognition Algorithms
, 1998
"... We study the complexity of image processing and pattern recognition (IPPR) algorithms by their representation as finite cellular automatabased structures. A universal model to represent multilayer homogeneous IPPR algorithms and a technique to compare their quality are required for problems of visio ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
We study the complexity of image processing and pattern recognition (IPPR) algorithms by their representation as finite cellular automatabased structures. A universal model to represent multilayer homogeneous IPPR algorithms and a technique to compare their quality are required for problems of vision system adaptation, learning, and by the systems for automatic programming. We propose the finite cellular automatabased model for representation of IPPR algorithms and sequential and parallel time complexity measures for this model. Composition and decomposition transformations of proposed structure are suggested and we show that in particular cases they can lead to reduction of complexity. Specific properties of IPPR tasks that are important for their complexity research are discussed.
Article A Novel Cloning Template Designing Method by Using an Artificial Bee Colony Algorithm for Edge Detection of CNN Based Imaging Sensors
, 2011
"... sensors ..."
(Show Context)
Error Tolerance In Cnns. Application To The Design Of Robust Cnns
"... This paper deals with the obtention of robust parameter configurations for DTCNNs and for a class of CTCNNs (here called CTCNNs with Discrete Configurations, DCCTCNN), in the presence of additive and multiplicative implementation errors. Expressions that characterize the tolerance to both multi ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
This paper deals with the obtention of robust parameter configurations for DTCNNs and for a class of CTCNNs (here called CTCNNs with Discrete Configurations, DCCTCNN), in the presence of additive and multiplicative implementation errors. Expressions that characterize the tolerance to both multiplicative and additive errors caused by circuit inaccuracies in DTCNNs and DCCTCNNs VLSI implementation are first deduced. Taking into account those expressions it is proposed to obtain robust parameter configurations, by using a design process based on local rules, as the solution of a single linear programming problem. The process is applied to the generation of robust configuration for some tasks. The tolerance to errors of these configurations has been corroborated by simulations. The differences in parameter values and tolerance to errors, between the robust configuration obtained for solving a particular task in DTCNNs and that obtained in DCCTCNNs, are given.
2002 Kluwer Academic Publishers. Manufactured in The Netherlands. Parameter Configurations for Hole Extraction in Cellular Neural Networks (CNN)
, 2001
"... Abstract. It is shown that the holes of the objects in an input image with a CTCNN [1] or a DTCNN [2] may be obtained in a single transient using just one linear parameter configuration. A set of local rules is given that describe how a CNN with a linear configuration may extract the hole of the o ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract. It is shown that the holes of the objects in an input image with a CTCNN [1] or a DTCNN [2] may be obtained in a single transient using just one linear parameter configuration. A set of local rules is given that describe how a CNN with a linear configuration may extract the hole of the objects of an input image in a single transient. The parameter configuration for DTCNNs or for CTCNNs is obtained as the solution of a single linear programming problem, including robustness as an objective. The tolerances to multiplicative and additive errors caused by circuit inaccuracies for the linear holeextraction configurations proposed have been deduced. These tolerable errors have been corroborated by simulations. The tolerance to errors and the speed of the CTCNN linear configuration proposed for hole extraction are compared with those of the CTCNN nonlinear configuration found in the bibliography [3]. Key Words: cellular neural networks, hole extraction, tolerance to errors, linear programming problem 1.
On the Cellbased Complexity of Recognition of Bounded Configurations by Finite Dynamic Cellular Automata
, 2002
"... This paper studies complexity of recognition of classes of bounded configurations by a generalization of conventional cellular automata (CA)  finite dynamic cellular automata (FDCA). Inspired by the CAbased models of biological and computer vision, this study attempts to derive the properties of ..."
Abstract
 Add to MetaCart
(Show Context)
This paper studies complexity of recognition of classes of bounded configurations by a generalization of conventional cellular automata (CA)  finite dynamic cellular automata (FDCA). Inspired by the CAbased models of biological and computer vision, this study attempts to derive the properties of a complexity measure and of the classes of input configurations that make it beneficial to realize the recognition via a twolayered automaton as compared to a onelayered automaton. A formalized model of an image pattern recognition task is utilized to demonstrate that the derived conditions can be satisfied for a nonempty set of practical problems.
Abstract
, 2002
"... This paper studies complexity of recognition of classes of bounded configurations by a generalization of conventional cellular automata (CA) — finite dynamic cellular automata (FDCA). Inspired by the CAbased models of biological and computer vision, this study attempts to derive the properties of ..."
Abstract
 Add to MetaCart
(Show Context)
This paper studies complexity of recognition of classes of bounded configurations by a generalization of conventional cellular automata (CA) — finite dynamic cellular automata (FDCA). Inspired by the CAbased models of biological and computer vision, this study attempts to derive the properties of a complexity measure and of the classes of input configurations that make it beneficial to realize the recognition via a twolayered automaton as compared to a onelayered automaton. A formalized model of an image pattern recognition task is utilized to demonstrate that the derived conditions can be satisfied for a nonempty set of practical problems.