PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 8070806

Nonlinear parameter estimation by linear association: application to a five-parameter passive neuron model.

B Tawfik·D M Durand
View original source ↗Export metadata ↓

Abstract

Linear associative memories (LAM) have been intensely used in the areas of pattern recognition and parallel processing for the past two decades. Application of LAM to nonlinear parameter estimation, however, has only been recently attempted. The process consists in converting the nonlinear function in the parameters into a set of linear algebraic equations. The nature of the linearized system and the factors influencing the accuracy of the parameter estimates have not yet been fully investigated. In this paper, LAM is applied to a nonlinear five-parameter model of the neuron. Ill-conditioning, which is often exhibited in LAM, is treated with the method of regularization as well as by the singular value decomposition (SVD). Simulation results indicate that the parameters estimated by LAM exhibit a remarkable robustness against additive white noise in comparison with the classical gradient optimization technique. Moreover, it is shown that regularization can be superior to SVD under certain conditions. Our results suggest that LAM can be used both as a noise reduction technique and as a stand-alone nonlinear parameter estimation algorithm. The comparison between LAM and a gradient technique show that, for this estimation problem, the LAM method can give more reliable estimates. Further improvements in estimation quality may still be achieved by the use of other forms of regularizing functions.

Explore related subjects

Linear ModelsModels, NeurologicalNeuronsNonlinear DynamicsJournal ArticleResearch Support, U.S. Gov't, Non-P.H.S.Research Support, U.S. Gov't, P.H.S.

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

B Tawfik, D M Durand. 1994. Nonlinear parameter estimation by linear association: application to a five-parameter passive neuron model.. https://doi.org/10.1109/10.293221

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2025

A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data.

Transfer learning aims to integrate useful information from multi-source datasets to improve the learning performance of target data. This can be effectively applied in genomics when we learn the gene associations in a target tissue, and data from other tissues can be integrated. However, heavy-tail distribution and outliers are common in genomics data, which poses challenges to the effectiveness of current transfer learning approaches. In this paper, we study the transfer learning problem under high-dimensional linear models with t-distributed error (Trans-PtLR), which aims to improve the estimation and prediction of target data by borrowing information from useful source data and offering robustness to accommodate complex data with heavy tails and outliers. In the oracle case with known transferable source datasets, a transfer learning algorithm based on penalized maximum likelihood and expectation-maximization algorithm is established. To avoid including non-informative sources, we propose to select the transferable sources based on cross-validation. Extensive simulation experiments as well as an application demonstrate that Trans-PtLR demonstrates robustness and better performance of estimation and prediction when heavy-tail and outliers exist compared to transfer learning for linear regression model with normal error distribution. Data integration, Variable selection, T distribution, Expectation maximization algorithm, Genotype-Tissue Expression, Cross validation.

Linear Models↗
PubMed1995

A sensitometric comparison of Fuji Super HR-G and Kodak T-mat G panoramic films.

Film contrast, relative speed, and resolution of Fuji Super HR-G panoramic film were determined according to specifications of the American National Standards Institute and compared with those of Kodak T-mat G panoramic film. The films were simultaneously exposed by Kodak Lanex regular intensifying screens with time-scale sensitometry. Optical density was read with a digital densitometer, and characteristic curves were plotted and analyzed by polynomial and linear regression. The average gradients of the linear regression curves between 0.25 and 2.00 optical density units above base plus fog were taken as contrast (HR-G: 1.831, T-mat G: 1.712). Relative speed, when exposed with Lanex regular intensifying screens and calculated at 1.00 optical density unit above base plus fog, was 412 for HR-G. A speed of 400 was chosen for T-mat G to match Kodak consumer information. Resolution for both films was similar. These findings suggest that Fuji Super HR-G panoramic film develops similar contrast, speed, and resolution to Kodak T-mat G panoramic film.

Linear Models↗
PubMed1994

Some fundamental influences on the pathology requesting behaviour of Victorian general practitioners--preliminary study results.

The results are presented of a preliminary study of Australian medical practitioners who graduated in Victoria in the years 1983 to 1988, which was conducted to ascertain if there were fundamental influences that affected how these practitioners requested pathology services. Multivariate linear regression was used to analyze the data. The study suggests that the year of graduation, the hospital of first post-graduate attachment and the gender of the practitioner were significant influences on the requesting of pathology (p = 0.0001 for each of the 3 influences). The university of graduation was not found to be a significant influence in its own right, but became significant in some two-way and three-way interactions. Some possible explanations for the effect of these influences are discussed, and further study is now being undertaken by the author.

Linear Models↗