Finite word length arithmetic computational error effects on the LMS adaptive weights
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 628-631
- https://doi.org/10.1109/icassp.1977.1170185
Abstract
Finite word length arithmetic computational errors (due to roundoff, chopping, etc.), in on-line applications of the Widrow-Hoff LMS adaptive algorithm, result in statistical variations in the weight vector from the infinite precision arithmetic weight vector. These errors can be modeled as an additive driving noise in the weight computation algorithm, effecting weight mean and covariance convergence. Assuming stationary, independent Gaussian input data, the mean and covariance convergence conditions and bounds on the errors due to the additive noise are obtained. These bounds are tested for roundoff and chopping using 2's complement, fixed-point arithmetic with an adaptive noise canceller of Gaussian noise.Keywords
This publication has 5 references indexed in Scilit:
- Effect of Errors in Adaptive WeightsIEEE Transactions on Aerospace and Electronic Systems, 1976
- Stationary and nonstationary learning characteristics of the LMS adaptive filterProceedings of the IEEE, 1976
- Adaptive noise cancelling: Principles and applicationsProceedings of the IEEE, 1975
- A discrete model for product quantization errors in digital filtersIEEE Transactions on Audio and Electroacoustics, 1971
- A simple adaptive algorithm for real-time processing in antenna arraysProceedings of the IEEE, 1969