Title :
Characterization of Analog Local Cluster Neural Network Hardware for Control
Author :
Sitte, Joaquin ; Zhang, Liang ; Rueckert, Ulrich
Author_Institution :
Queensland Univ. of Technol., Brisbane
fDate :
7/1/2007 12:00:00 AM
Abstract :
The local cluster neural network (LCNN) was designed for analog realization especially suited to applications in control systems. It uses clusters of sigmoidal neurons to generate basis functions that are localized in multidimensional input space. Sigmoidal neurons are well suited to analog electronic realization. In this paper, we report the results of extensive measurements that characterize the computational capabilities of the first analog very large scale integration (VLSI) realization of the LCNN. Despite manufacturing fluctuations and the inherent low precision of analog electronics, the test results suggest that it may be suitable for use in feedback control systems.
Keywords :
control systems; neural nets; analog electronic realization; analog local cluster neural network hardware; analog very large scale integration realization; computational capability characterization; feedback control system; Analog computers; Control systems; Electronic equipment testing; Fluctuations; Manufacturing; Multidimensional systems; Neural network hardware; Neural networks; Neurons; Very large scale integration; Analog computation; analog very large scale integration (VLSI); function approximation; neural networks (NNs); radial basis function (RBF) networks; Algorithms; Cluster Analysis; Computer Simulation; Decision Support Techniques; Equipment Design; Equipment Failure Analysis; Feedback; Models, Theoretical; Neural Networks (Computer); Signal Processing, Computer-Assisted;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2007.899518
