Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

/pdf/the-graph-neural-network-model-1nfbg1hdkj.pdf

The Graph Neural Network Model

A novel class of information-processing systems called cellular neural networks is proposed. Like neural networks, they are large-scale nonlinear analog circuits that process signals in real time. Like cellular automata, they consist of a massive aggregate of regularly spaced circuit clones, called cells, which communicate with each other directly only through their nearest neighbors. Each cell is made of a linear capacitor, a nonlinear voltage-controlled current source, and a few resistive linear circuit elements. Cellular neural networks share the best features of both worlds: their continuous-time feature allows real-time signal processing, and their local interconnection feature makes them particularly adapted for VLSI implementation. Cellular neural networks are uniquely suited for high-speed parallel signal processing. >

http://dns2.asia.edu.tw/~ysho/YSHO-English/2000%20Engineering/PDF/IEEE%20Tra%20Cir%20Sys35,%201257.pdf

Cellular neural networks: theory

The theory of a novel class of information-processing systems, called cellular neural networks, which are capable of high-speed parallel signal processing, was presented in a previous paper (see ibid., vol.35, no.10, p.1257-72, 1988). A dynamic route approach for analyzing the local dynamics of this class of neural circuits is used to steer the system trajectories into various stable equilibrium configurations which map onto binary patterns to be recognized. Some applications of cellular neural networks to such areas as image processing and pattern recognition are demonstrated, albeit with only a crude circuit. In particular, examples of cellular neural networks which can be designed to recognize the key features of Chinese characters are presented. >

Cellular neural networks: applications

Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network

Neural networks for control systems: a survey

A novel class of information-processing systems called cellular neural networks is proposed. Like neural networks, they are large-scale nonlinear circuits which process signals in real time. Like cellular automata, they are made of a massive aggregate of regularly spaced circuit clones, called cells, which communicate with each other directly only through their nearest neighbors. Some applications in such areas as image processing are demonstrated, albeit with only a crude circuit. In particular, examples of cellular neural networks which can be designed to recognize the key features of Chinese characters are presented. Some theorems concerning the dynamic range and the steady states of cellular neural networks are proved. In view of the near-neighbor interactive property of cellular neural networks, they are much more amenable to VLSI implementation than general neural networks. >

/pdf/cellular-neural-networks-264aatw676.pdf

Cellular neural networks

A cellular neural network (CNN) which is an example of very-large-scale analog processing or collective analog computation is presented. The CNN architecture combines some features of fully connected analog neural networks with the nearest-neighbor interactions found in cellular automata. VLSI implementation of these circuits is discussed. Though the circuits described have been fabricated for noise removal and connected segment extraction, most of the features of the VLSI circuits are shared by VLSI implementations of other processing functions. >

VLSI implementation of cellular neural networks

The cellular neural network (CNN) is an example of very-large-scale analog processing or collective analog computation. The CNN architecture combines some features of fully connected analog neural networks with the nearest-neighbor interactions found in cellular automata. These networks have numerous advantages both for simulation and for VLSI implementation and can perform (though are not limited to) several important image processing functions. The important features which enable the CNN architecture to perform signal processing functions using standard VLSI technology are discussed. Circuit characteristics are outlined, and examples of cellular neural network signal processing are presented. Connected segment extraction is illustrated by examples, as is histogramming using a two-layer CNN. >

https://ieeexplore.ieee.org/iel5/143/3356/00112257.pdf

L. Yang

Papers

Cellular neural networks: theory

Cellular neural networks

VLSI implementation of cellular neural networks

Analog signal processing using cellular neural networks