Showing papers by "Lionel Tarassenko published in 1994"

A probabilistic resource allocating network for novelty detection

Abstract: The detection of novel or abnormal input vectors is of importance in many monitoring tasks, such as fault detection in complex systems and detection of abnormal patterns in medical diagnostics. We have developed a robust method for novelty detection, which aims to minimize the number of heuristically chosen thresholds in the novelty decision process. We achieve this by growing a gaussian mixture model to form a representation of a training set of "normal" system states. When previously unseen data are to be screened for novelty we use the same threshold as was used during training to define a novelty decision boundary. We show on a sample problem of medical signal processing that this method is capable of providing robust novelty decision boundaries and apply the technique to the detection of epileptic seizures within a data record.

Analogue Neural Vlsi: A Pulse Stream Approach

Abstract: From the Publisher: Analogue VLSI is an important medium for the implementation of neural networks and the authors' aim in this book is to explore this technique in detail. This book compares a variety of approaches, giving readers an appreciation of analogue neural VLSI through examples of each approach rather than by means of an exhaustive survey.

Robot path planning using VLSI resistive grids

Abstract: The resistive grid algorithm for mobile robot path planning is described. A major advantage of the method is that it is capable of a fine-grained parallel analogue VLSI implementation, which offers a fast, low-power solution to the problem of mobile robot navigation. The results from a small-scale test chip are presented, together with their implications for scaling up to a full-sized path-planning chip.