Craig L. Fancourt

Optimization in companion search spaces: The case of cross-entropy and the Levenberg-Marquardt algorithm (2007)

Craig L. Fancourt, Jose C. Principe

We present a new learning algorithm for the supervised training of multilayer perceptrons for classification that is significantly faster than any previously known method. Like existing methods, the...

The coherence function in blind source separation of convolutive mixtures of non-stationary signals (2001)

Craig L. Fancourt, Lucas Parra

We propose a new performance criteria and update mechanism for the blind decorrelation of an array of sensor measurements into independent sources, assuming each sensor measures a different...

On the use of Neural Networks in the Generalized Likelihood Ratio Test for Detecting Abrupt Changes in Signals (2000)

Craig Fancourt And, Craig L. Fancourt, Jose C. Principe

With the advent of efficient algorithms and fast computers for training neural networks, it is now feasible to employ neural network predictors in the generalized likelihood ratio (GLR) test for the...

On the Relationship between the Karhunen-Loeve Transform and the Prolate Spheroidal Wave Functions (2000)

Craig L. Fancourt, Jose C. Principe

We find a close relationship between the discrete KarhunenLoeve transform (KLT) and the discrete prolate spheroidal wave functions (DPSWF). We show that the DPSWF form a natural basis for an...

On the use of Neural Networks in the Generalized Likelihood Ratio Test for Detecting Abrupt Changes in Signals (2000)

Craig L. Fancourt, Jose C. Principe

With the advent of efficient algorithms and fast computers for training neural networks, it is now feasible to employ neural network predictors in the generalized likelihood ratio (GLR) test for the...

Modeling time dependencies in the mixture of experts (1998)

Craig L. Fancourt, Jose C. Principe

The Mixture of Experts, as it was originally formulated, is a static algorithm in the sense that the output of the network, and parameter updates during training, are completely independent from one...

Competitive Principal Component Analysis for Locally Stationary Time Series (1998)

Jose C. Principe, Ph. D, Craig L. Fancourt, Craig L. Fancourt, Jose C. Principe, ...

A new unsupervised algorithm is proposed that performs competitive principal component analysis (PCA) of a time series. A set of expert PCA networks compete, through the Mixture of Experts (MOE)...

Temporal Self-Organization Through Competitive Prediction (1997)

Craig L. Fancourt, Jose C. Principe

Two self-organizing principles for the competitive identification of piecewise stationary time series are described. In the first, a neighborhood map of one step predictors competes for the data...

A Neighborhood Map of Competing One Step Predictors for Piecewise Segmentation and Identification of Time Series (1996)

Craig L. Fancourt, Jose C. Principe

Abstract–A new off-line technique for the competitive identification of piecewise stationary time series is described. A neighborhood map of one step predictors competes for the data during...

A Neighborhood Map of Competing One Step Predictors for Piecewise Segmentation and Identification of Time Series (1996)

Craig Fancourt And, Craig L. Fancourt, Jose C. Principe

A new off-line technique for the competitive identification of piecewise stationary time series is described. A neighborhood map of one step predictors competes for the data during training. The...

A Neighborhood Map of Competing One Step Predictors for Piecewise Segmentation and Identification of Time Series (1996)

Craig L. Fancourt, Jose C. Principe

A new off-line technique for the competitive identification of piecewise stationary time series is described. A neighborhood map of one step predictors competes for the data during training. The...