Automated Design of Neural Network Architecture for Classification

Abstract

<p>This Ph.D. thesis deals with finding a good architecture of a neural network classifier. The focus is on methods to improve the performance of existing architectures (i.e. architectures that are initialised by a good academic guess) and automatically building neural networks. An introduction to the Multi-Layer feed-forward neural network is given and the most essential properties for neural networks; there ability to learn from examples is discussion. Topics like traning and generalisation are treated in more explicit. On the basic of this dissuscion methods for finding a good architecture of the network described. This includes methods like; Early stopping, Cross validation, Regularisation, Pruning and various constructions algorithms (methods that successively builds a network). New ideas of combining units with different types of transfer functions like radial basis functions and sigmoid or threshold functions led to the development of a new construction algorithm for classification. The algorithm called "GLOCAL" is fully described. Results from these experiments real life data from a <em>Synthetic Aperture Radar (SAR)</em> are provided.</p><p>The thesis was written so people from the industry and graduate students who are interested in neural networks hopeful would find it useful.</p><p><strong>Key words</strong>: Neural networks, Architectures, Training, Generalisation deductive and construction algorithms.</p>