This thesis explores the relationship between two classification models: decision trees and multilayer perceptrons. Decision trees carve up databases into box-shaped regions, and make predictions based on the majority class in each box. They are quick to build and relatively easy to interpret. Multilayer perceptrons (MLPs) are often more accurate than decision trees, because they are able to use soft, curved, arbitrarily oriented decision boundaries. Unfortunately MLPs typically require a great deal of effort to determine a good number and arrangement of neural units, and then require many passes through the database to determine a good set of connection weights. The cost of creating and training an MLP is thus hundreds of times greater than the cost of creating a decision tree, for perhaps only a small gain in accuracy. The following scheme is proposed for reducing the computational cost of creating and training MLPs. First, build and prune a decision tree to generate prior knowledge of the database. Then, use that knowledge to determine the initial architecture and connection weights of an MLP. Finally, use a training algorithm to refine the knowledge now embedded in the MLP. This scheme has two potential advantages: a suitable neural network architecture is determined very quickly, and training should require far fewer passes through the data. In this thesis, new algorithms for initialising MLPs from decision trees are developed. The algorithms require just one traversal of a decision tree, and produce four-layer MLPs with the same number of hidden units as there are nodes in the tree. The resulting MLPs can be shown to reach a state more accurate than the decision trees that initialised them, in fewer training epochs than a standard MLP. Employing this approach typically results in MLPs that are just as accurate as standard MLPs, and an order of magnitude cheaper to train.

Thesis (Ph. D.)--University of Washington, 2001. / Vita. Includes bibliographical references (leaves 59-63).

This thesis is concerned with the use of neural networks for motor control tasks. The main goal of the thesis is to investigate ways in which the biological notions of motor programs and Central Pattern Generators (CPGs) may be implemented in a neural network framework. Biological CPGs can be seen as components within a larger control scheme, which is basically modular in design. In this thesis, these ideas are investigated through the use of modular recurrent networks, which are used in a variety of control tasks. The first experimental chapter deals with learning in recurrent networks, and it is shown that CPGs may be easily implemented using the machinery of backpropagation. The use of these CPGs can aid the learning of pattern generation tasks; they can also mean that the other components in the system can be reduced in complexity, say, to a purely feedforward network. It is also shown that incremental learning, or 'shaping' is an effective method for building CPGs. Genetic algorithms are also used to build CPGs; although computational effort prevents this from being a practical method, it does show that GAs are capable of optimising systems that operate in the context of a larger scheme. One interesting result from the GA is that optimal CPGs tend to have unstable dynamics, which may have implications for building modular neural controllers. The next chapter applies these ideas to some simple control tasks involving a highly redundant simulated robot arm. It was shown that it is relatively straightforward to build CPGs that represent elements of pattern generation, constraint satisfaction. and local feedback. This is indirect control, in which errors are backpropagated through a plant model, as well as the ePG itself, to give errors for the controller. Finally, the third experimental chapter takes an alternative approach, and uses direct control methods, such as reinforcement learning. In reinforcement learning, controller outputs have unmodelled effects; this allows us to build complex control systems, where outputs modulate the couplings between sets of dynamic systems. This was shown for a simple case, involving a system of coupled oscillators. A second set of experiments investigates the use of simplified models of behaviour; this is a reduced form of supervised learning, and the use of such models in control is discussed.

Thesis (Ph. D.)--Faculty of Pharmacy, University of Sydney, 2004. / Bibliography: leaves 217-253.

Thesis (M.S.)--Virginia Polytechnic Institute and State University, 1992. / Vita. Abstract. Includes bibliographical references (leaves 80-81). Also available via the Internet.

Thesis (Ph. D.)--University of Sydney, 2003. / Title from title screen (viewed Apr. 28, 2008). Submitted in fulfilment of the requirements for the degree of Doctor of Philosophy to the Faculty of Pharmacy. Includes bibliography. Also available in print form.

Thesis (Ph. D.)--Lehigh University, 1998. / Includes vita. Includes bibliographical references (leaves 181-185).

Thesis (Master)--İzmir Institute Of Technology, İzmir, 2006. / Keywords: Neural networks, Hybrid systems Includes bibliographical references (leaves. 83-85).

Thesis (M. Sc.)--University of Hong Kong, 1995. / Includes bibliographical references.

Report (M.S.)--Virginia Polytechnic Institute and State University, 1993. / Abstract. Includes bibliographical references (leaf 45). Also available via the Internet.