Robust low-sensitivity Adaline neuron based on Continuous Valued Number System

Authors:
Mitra Mirhassani;Majid Ahmadi;Graham A. Jullien
Affiliations:
Research Centre for Integrated Microsystems (RCIM), Electrical and Computer Engineering, University of Windsor, Windsor, Canada N9B 3P4;Research Centre for Integrated Microsystems (RCIM), Electrical and Computer Engineering, University of Windsor, Windsor, Canada N9B 3P4;Advanced Technology Information Processing Systems Laboratories (ATIPS), University of Calgary, Calgary, Canada T2N 1N4
Venue:
Analog Integrated Circuits and Signal Processing
Year:
2008

Citing 6
Cited 2

Accuracy vs. Precision in Digital VLSI Architectures for Signal Processing

IEEE Transactions on Computers
Weight perturbation: An optimal architecture and learning technique for analog vlsi feedforward and recurrent multilayer networks

Neural Computation
Sensitivity analysis of neocognitron

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Sensitivity analysis of multilayer perceptron to input and weight perturbations

IEEE Transactions on Neural Networks
The selection of weight accuracies for Madalines

IEEE Transactions on Neural Networks
Sensitivity analysis of single hidden-layer neural networks with threshold functions

IEEE Transactions on Neural Networks

Resistive-type CVNS distributed neural networks with improved noise-to-signal ratio

IEEE Transactions on Circuits and Systems II: Express Briefs
Analog implementation of a novel resistive-type sigmoidal neuron

IEEE Transactions on Very Large Scale Integration (VLSI) Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article Continuous Valued Number System is studied as an alternative method for implementing Analog Neural Networks. Continuous Valued Number System is analog in nature and employs digit level analog modular arithmetic. The information redundancy among the digits allows efficient operations using analog circuitry with arbitrary accuracy. The general operations in this number system are more precise than regular analog operations, thus enabling us to implement large size analog neural networks with more precision. In this article, function evaluation properties of the Continuous Valued Number System are introduced. These key properties are used for developing analog Adaline with a nonlinear activation function. Stochastic modeling of a network of such elements is carried out which indicates that the proposed network has low sensitivity to implementation errors.