Search Results - "Manry, M.T."
-
1
Feature Selection Using a Piecewise Linear Network
Published in IEEE transactions on neural networks (01-09-2006)“…We present an efficient feature selection algorithm for the general regression problem, which utilizes a piecewise linear orthonormal least squares (OLS)…”
Get full text
Journal Article -
2
Comparison of very short-term load forecasting techniques
Published in IEEE transactions on power systems (01-05-1996)“…Three practical techniques-fuzzy logic (FL), neural networks (NN), and autoregressive models-for very short-term power system load forecasting are proposed and…”
Get full text
Journal Article Conference Proceeding -
3
Efficient machine learning approach for optimizing the timing resolution of a high purity germanium detector
Published in Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment (21-11-2020)“…We describe here an efficient machine-learning based approach for the optimization of parameters used for extracting the arrival time of waveforms, in…”
Get full text
Journal Article -
4
LMS learning algorithms: misconceptions and new results on converence
Published in IEEE transactions on neural networks (01-01-2000)“…The Widrow-Hoff delta rule is one of the most popular rules used in training neural networks. It was originally proposed for the ADALINE, but has been…”
Get full text
Journal Article -
5
-
6
A modified hidden weight optimization algorithm for feedforward neural networks
Published in Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002 (2002)“…The output weight optimization-hidden weight optimization (OWO-HWO) feedforward network training algorithm alternately solves linear equations for output…”
Get full text
Conference Proceeding
-
7
Conventional modeling of the multilayer perceptron using polynomial basis functions
Published in IEEE transactions on neural networks (01-01-1993)“…A technique for modeling the multilayer perceptron (MLP) neural network, in which input and hidden units are represented by polynomial basis functions (PBFs),…”
Get full text
Journal Article -
8
Demodulation for wireless ATM network using modified SOM network
Published in 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing (2004)“…We study the demodulation problem in time division multiple access (TDMA) wireless asynchronous transfer mode (ATM) networks, where Rician flat fading channels…”
Get full text
Conference Proceeding -
9
A robust statistical-based estimator for soil moisture retrieval from radar measurements
Published in IEEE transactions on geoscience and remote sensing (01-01-1997)“…The authors examine the use of a robust statistical inversion approach to the estimation of soil moisture and roughness statistics from backscatter…”
Get full text
Journal Article Conference Proceeding -
10
Optimal pruning of feedforward neural networks based upon the Schmidt procedure
Published in Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002 (2002)“…A common way of designing feedforward networks is to obtain a large network and then to prune less useful hidden units. Here, two non-heuristic pruning…”
Get full text
Conference Proceeding -
11
New training algorithms for dependency initialized multilayer perceptrons
Published in The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 (2003)“…Due to the chaotic nature of multilayer perceptron training, training error usually fails to be a monotonically nonincreasing function of the number of hidden…”
Get full text
Conference Proceeding -
12
A self-organizing system for the development of neural network parameter estimators
Published in Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing (1995)“…The design an optimal neural network estimator from training data is difficult because: 1) the required complexity of the estimation network is unknown, 2)…”
Get full text
Conference Proceeding -
13
Enhanced robustness of multilayer perceptron training
Published in Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002 (2002)“…Due to the chaotic nature of multilayer perceptron training, training error usually fails to be a monotonically non-increasing function of the number of hidden…”
Get full text
Conference Proceeding -
14
Evaluation and improvement of two training algorithms
Published in Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002 (2002)“…Two effective neural network training algorithms are output weight optimization - hidden weight optimization and conjugate gradient. The former performs better…”
Get full text
Conference Proceeding -
15
An efficient, noise tolerant, linear extrapolator
Published in ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing (1988)“…The extrapolation algorithms are commonly used to replace large intervals of bad or missing data, given knowledge of the original signal's autocovariance or…”
Get full text
Conference Proceeding -
16
Convergent design of a piecewise linear neural network
Published in IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339) (1999)“…A piecewise linear neural network (PLNN) is discussed which maps N-dimensional input vectors into M-dimensional output vectors. A convergent algorithm for…”
Get full text
Conference Proceeding -
17
Fingerprint Feature Compression Using Statistical Coding Techniques
Published in 2009 Annual IEEE India Conference (01-12-2009)“…We have proposed a new fingerprint feature compression scheme, which extracts the fingerprint feature using pseudo-spectral fusion approach and compresses the…”
Get full text
Conference Proceeding -
18
A pseudospectral fusion approach to fingerprint matching
Published in Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004 (2004)“…A prototype fingerprint verification system is described which combines the direction and density images into a complex pseudo-spectrum. Two methods for…”
Get full text
Conference Proceeding -
19
A complexity estimation approach for estimating neural net size
Published in Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers (1995)“…A complexity estimation technique is developed for predicting the number of hidden units a multilayer perceptron (MLP) requires to reach a given performance…”
Get full text
Conference Proceeding -
20
Progressive image transmission
Published in IEEE transactions on circuits and systems for video technology (01-10-1993)“…Progressive image transmission (PIT) is widely used in many applications, since it generates the successively improved reconstructions of an image. In spatial…”
Get full text
Journal Article