Cellular neural networks: applications

Chua, Leon O.; Yang, Lin-Bao

doi:10.1109/31.7601

Cited by 2,159 publications

(738 citation statements)

References 10 publications

Supporting

Mentioning

732

Contrasting

Unclassified

Order By: Relevance

“…A two-dimensional continuous time zero-input CNN consisting of n = M N cells in a M ×N array, as first introduced by Chua and Yang [1], can be described bẏ…”

Section: Preliminariesmentioning

confidence: 99%

“…The interconnection topology of the network can be described by an adjacency matrix S, and thus a weight T ij is non-zero only if S ij = 1. Vector α ∈ H n is a memory vector for (1) if the latter has an asymptotically stable equilibrium point β ∈ R n such that α = sat (β) [1].…”

Section: Preliminariesmentioning

confidence: 99%

“…The adjacency matrix S which determines which T ij , typically encodes a lattice structure and can be selected arbitrarily as long as certain conditions are satisfied [1], [3], [4]: If α ∈ B n and β = T α + b are such that (2) then (α, β) is a pair of a memory vector and an asymptotically stable equilibrium point of system (1). Also if α ∈ B n and β = T α + b are such that for any i = 1, .…”

Section: Preliminariesmentioning

confidence: 99%

“…In addition to aforementioned stability criteria, specific stability and robustness properties for these networks are established in terms of the elements of the network's weight matrix T and bias vector b [1], [3], [4]:…”

Section: Preliminariesmentioning

confidence: 99%

“…A cellular neural network (CNN) is a nonlinear dynamical system, implementing an associative memory, where neuron interactions are limited to the neighboring units only [1]. Research on the design and synthesis of these types of networks has gained increasing attention in recent years because of their topology being relatively sparse, which makes them a promising choice for very-large-scale integration implementations.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Topology optimization in cellular neural networks

Bhambhani

Tanner

2010

49th IEEE Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

Abstract-This paper presents a constrained combinatorial optimization approach to the design of cellular neural networks with sparse connectivity. The method applies to cases where maintaining links between neurons incurs a cost, which could possibly vary between these links. The interconnection topology of the cellular neural network is diluted without significantly degrading its performance, the latter quantified by the average recall probability for the desired patterns engraved into its associative memory. The dilution process selectively removes the links that contribute the least to a metric related to the size of system's desired memory pattern attraction regions. The metric used here is the magnitude of the network's nodes' stability parameters, which have been proposed as a measure for the quality of memorization. We demonstrate by means of an example that this method of network dilution produces cheaper associative memories that in general trade off performance for cost, and in many cases the performance of the diluted network is on par with the original system.Index Terms-Cellular neural networks, stability parameters, sparse associative memory.

show abstract

“…A two-dimensional continuous time zero-input CNN consisting of n = M N cells in a M ×N array, as first introduced by Chua and Yang [1], can be described bẏ…”

Section: Preliminariesmentioning

confidence: 99%

Section: Preliminariesmentioning

confidence: 99%

Section: Preliminariesmentioning

confidence: 99%

Section: Preliminariesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Topology optimization in cellular neural networks

Bhambhani

Tanner

2010

49th IEEE Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

show abstract

Analogue Combinatorics and Cellular Automata—key Algorithms and Lay-Out Design

Venetianer

Szolgay

Crounse

et al. 1996

Int. J. Circ. Theor. Appl.

View full text Add to dashboard Cite

This paper demonstrates how certain logic and combinatorial tasks can be solved using CNNs. A design method is proposed for solving combinatorial tasks on a CNN. It can be used to simulate cellular automata on a CNN, to prove the self‐reproducing capability of the CNNUM and for sorting, histogram calculation, parity analysis and minimum Hamming distance computation. These solutions are especially useful since they can serve as subroutines of more complex CNNUM algorithms. As an important real‐life application the lay‐out of printed circuit boards is designed with the CNNUM at an extremely high speed.

show abstract

A CNN Universal Chip in Cmos Technology

Espejo

Carmona

Domínguez-Castro

et al. 1996

Int. J. Circ. Theor. Appl.

View full text Add to dashboard Cite

This paper describes the design of a programmable cellular neural network (CNN) chip with added functionalities similar to those of the CNN universal machine. The prototype contains 1024 cells and has been designed in a 1·0 μm, n‐well CMOS technology. Careful selection of the topology and design parameters has resulted in a cell density of 31 cells mm−2 and around 7–8 bits accuracy in the weight values. Adaptive techniques have been employed to ensure accurate external control and system robustness against process parameter variations.

show abstract

Cellular neural networks: applications

Cited by 2,159 publications

References 10 publications

Topology optimization in cellular neural networks

Topology optimization in cellular neural networks

Analogue Combinatorics and Cellular Automata—key Algorithms and Lay-Out Design

A CNN Universal Chip in Cmos Technology

Contact Info

Product

Resources

About