Juin J. Liou

Design of gratings and frequency selective surfaces using fuzzy ARTMAP neural networks

This paper presents a study of the Fussy ARTMAP neural network in designing cascaded gratings and frequency selective surfaces (FSS) in general. Conventionally, trial and error procedures are used until an FSS matches the design criteria. One way of avoiding this laborious process is to use neural networks (NNs). A neural network can be trained to predict the dimensions of the elements comprising the FSS structure, their distance of separation, and their shape required to produce the desired frequency response. In the past, the multi-layer perception architecture trained with the back-prop learning algorithm (back-prop network) was used to solve this problem. Unfortunately, the back-prop network experiences, at times, convergence problems and these problems become amplified as the size of the training set increases. In this work, the Fussy ARTMAP neural network is used to address the FSS design problem. The Fussy ARTMAP neural network converges much faster than the back-prop network, and most importantly its convergence to a solution is guaranteed. Several results (frequency responses) from cascaded gratings corresponding to various angles of wave incidence, layer separation, width strips, and interstrip separation are presented and discussed

A Mixed Analog/Digital VLSI Design and Simulation of An Adaptive Resonance Theory (ART) Neural Network Architecture

This paper presents a mixed analog/digital circuit design and simulation for an architecture called the augmented adaptive resonance theory-1 neural network (AART1-NN). The circuit is implemented based on the transconductance-mode approach and mixed analog/digital components, in which analog circuits are used to fully incorporate the parallel mechanism of the neural network, whereas digital circuits are used to provide a reduced circuit size as well as more precise multiplication operation. The AART1-NN circuit implemented is simulated using Pspice, and the results are in good agreement with those calculated numerically from the coupled nonlinear differential equations governing the AART1-NN.

Mixed analog/digital VLSI design and simulation of an adaptive resonance theory (ART) neural network architecture

This paper presents a mixed analog/digital circuit design for an adaptive resonance theory (ART) architecture, called the augmented adaptive resonance theory-I neural network (AART1-NN). The circuit is implemented based on the transconductance-mode approach and mixed analog/digital components, in which analog circuits are used to fully incorporate the parallel mechanism of the neural network, whereas digital circuits are used to provide a reduced circuit size as well as more precise multiplication operation. It is shown that the Pspice simulation results of the implemented circuit are in good agreement with the results calculated numerically from the coupled nonlinear differential equations governing the AART1-NN.

Design of gratings and frequency-selective surfaces using ARTMAP neural networks

This paper presents a study of the Fuzzy ARTMAP neural network in designing cascaded gratings and Frequency Selective Surfaces (FSS) in general. Conventionally, trial-and-error procedures are used until an FSS matches the design criteria. One way of avoiding this laborious and manual process is to use neural networks. A neural network can be trained to predict the dimensions of the metallic patches (or apertures), their distance of separation, their shape, and the number of layers required in a multilayer structure which gives the desired frequency response. In the past, to achieve this goal, the backpropagation (backprop) learning algorithm was used in conjunction with an inversion algorithm. Unfortunately, the backprop algorithm sometimes has problems with convergence. In this work the Fuzzy ARTMAP neural networks is utilized. The Fuzzy ARTMAP is faster to train than the backprop and it does not require an inversion algorithm to solve the FSS problem. Most importantly, its convergence is guaranteed. Several results (frequency responses) from cascaded gratings for various angles of wave incidence, layer separation, width strips, and interstrip separation are presented and discussed.

Hardware implementation of ART1 memories using a mixed analog/digital approach

This paper presents a VLSI circuit implementation for both the short-term memory (STM) and long-term memory (LTM) of the adaptive resonance theory neural network (ART1-NN). The circuit is implemented based on the transconductance-mode approach and mixed analog/digital components, in which analog circuits are used to fully incorporate the parallel mechanism of the neural network, whereas digital circuits provide a reduced circuit size as well as a more precise multiplication operation. A simple analog-to-digital (A/D) converter is also included to realize binary STM activities and characterize the quenching threshold. The PSpice simulation results of the implemented circuits are in good agreement with the exact solutions of the coupled nonlinear differential equations.<<ETX>>

Hardware implementation of an adaptive resonance theory (ART) neural network using compensated operational amplifiers

This paper presents an analog circuit design and implementation for an adaptive resonance theory neural network architecture called the augmented ART1 neural network (AART1-NN). Practical monolithic operational amplifiers (Op-Amps) LM741 and LM318 are selected to implement the circuit, and a simple compensation scheme is developed to adjust the Op-Amp electrical characteristics to meet the design requirement. A 7-node prototype circuit has been designed and verified using the Pspice circuit simulator run on a Sun workstation. Results simulated from the AART1-NN circuit using the LM741, LM318, and ideal Op-Amps are presented and compared.

Analog circuit design and implementation of an adaptive resonance theory (ART) neural network architecture

This paper presents an analog circuit implementation for an adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AART1-NN). The AART1-NN is a modification of the popular ART1-NN, developed by Carpenter and Grossberg, and it exhibits the same behavior as the ART1-NN. The AART1-NN is a real-time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AART1-NN model. The circuit is implemented by utilizing analog electronic components, such as, operational amplifiers, transistors, capacitors, and resistors. The implemented circuit is verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from the PSpice circuit simulation compare favorably with simulation results produced by solving the differential equations numerically. The prototype system developed here can be used as a building block for larger AART1-NN architectures, as well as for other types of ART architectures that involve the AART1-NN model.