Neural networks applied to signal processing
Baehre, Mark D.
Therrien, Charles W.
MetadataShow full item record
The relationship between the structure of a neural network and its ability to perform nonlinear mapping is analyzed. A new algorithm, called the conjugate gradient optimization method, for calculating the weights and thresholds of a neural network is presented. The performance of the conjugate gradient algorithm is then compared to the well known backpropagation method and shown to be more computationally efficient. A neural network using the conjugate gradient algorithm is then applied to three simple examples to demonstrate its signal processing capabilities. The first example illustrates the ability of the neural network to perform classification. The second compares the performance of a one-step linear predictor to a neural network for a nonlinear chaotic time series. The neural network predictor is shown to provide much greater accuracy than its linear counterpart. The final application presented demonstrates the ability of a neural network to perform channel equalization for a nonmininmum phase channel. Its performance is then compared to its linear equivalent.
Approved for public release; distribution in unlimited.
Showing items related by title, author, creator and subject.
Chen, Chia-sheng (Monterey, California. Naval Postgraduate School, 2000-06);Classification trees and neural networks are widely used individually, yet little is known about the effect of combining these two techniques. Earlier work has shown that using k-nearest neighbor (k-NN) inside the leaves ...
Nedresky, Donald L. (Monterey, California: Naval Postgraduate School, 1990-09);An adaptive control system is a system that detects changes in the plant parameters and makes necessary adjustments to the systems performance. This thesis examines the use of parallel distributed processing systems (neural ...
Schaus, Brian M. (Monterey, California: Naval Postgraduate School, 2015-03);Techniques for classifying maritime domain targets-of-interest within images are explored in this thesis. Geometric and photometric features within each image are extracted from processed images and are used to train a ...