Search

Your search keyword '"D. E. Waagen"' showing total 6 results
Start Over Author "D. E. Waagen"
6 results on '"D. E. Waagen"'

1. EVOLVING CASCADE-CORRELATION NETWORKS FOR TIME-SERIES FORECASTING

Author

D. E. Waagen and J. R. McDonnell

Subjects
Artificial neural network, Mathematical model, Artificial Intelligence, business.industry, Computer science, Learning network, Cascade correlation, Artificial intelligence, Time series, business, Machine learning, computer.software_genre, computer
Abstract

This investigation applies evolutionary search to the cascade-correlation learning network. Evolutionary search is used to find both the input weights and input connectivity of candidate hidden units. A time-series prediction example is used to demonstrate the capabilities of the proposed approach.

Published
1994

4. Neural Network Construction Using Evolutionary Search

Author

J. R. McDonnell, D. E. Waagen, and W. C. Page

Subjects
Computer science, business.industry, Evolutionary robotics, Evolutionary algorithm, Machine learning, computer.software_genre, Evolutionary computation, Evolutionary acquisition of neural topologies, Evolutionary music, Genetic algorithm, Artificial intelligence, Evolution strategy, business, computer, Evolutionary programming
Abstract

This work investigates the application of evolutionary search for training candidate hidden units in cascade-correlation learning architectures. A hybrid evolutionary search algorithm which implements techniques from evolutionary programming and evolution strategies is proposed. This approach is evaluated on selected low-dimensional examples which are non-linearly separable. (AN)

Published
1994

6. Evolving Wavelet Compression Strategies

Author

J. D. Argast, J. R. McDonnell, and D. E. Waagen

Subjects
Discrete wavelet transform, Lifting scheme, Computer science, business.industry, Stationary wavelet transform, Second-generation wavelet transform, MathematicsofComputing_NUMERICALANALYSIS, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Wavelet transform, Pattern recognition, Data_CODINGANDINFORMATIONTHEORY, Wavelet packet decomposition, Wavelet, Computer vision, Artificial intelligence, business, Harmonic wavelet transform
Abstract

Wavelet theory provides an attractive approach to signal and image compression. This work investigates a new approach for wavelet transform coefficient selection for efficient image compression. This approach is based on the stochastic optimization of wavelet scale thresholds. Experimental results are compared with results from previously published wavelet image compression strategies. Evolutionary programming, Neural networks, Signal detection.

Published
1994

Catalog

Books, media, physical & digital resources
See catalog results