Noel E. Sharkey

AIJ Journal 2000 Journal Article

J.A. Anderson and E. Rosenfeld (Eds.), Talking Nets: An Oral History of Neural Networks

• Noel E. Sharkey

KER Journal 1997 Journal Article

Combining diverse neural nets

• AMANDA J. C. SHARKEY
• Noel E. Sharkey

An appropriate use of neural computing techniques is to apply them to problems such as condition monitoring, fault diagnosis, control and sensing, where conventional solutions can be hard to obtain. However, when neural computing techniques are used, it is important that they are employed so as to maximise their performance, and improve their reliability. Their performance is typically assessed in terms of their ability to generalise to a previously unseen test set, although unless the training set is very carefully chosen, 100% accuracy is rarely achieved. Improved performance can result when sets of neural nets are combined in ensembles and ensembles can be viewed as an example of the reliability through redundancy approach that is recommended for conventional software and hardware in safety-critical or safety-related applications. Although there has been recent interest in the use of neural net ensembles, such techniques have yet to be applied to the tasks of condition monitoring and fault diagnosis. In this paper, we focus on the benefits of techniques which promote diversity amongst the members of an ensemble, such that there is a minimum number of coincident failures. The concept of ensemble diversity is considered in some detail, and a hierarchy of four levels of diversity is presented. This hierarchy is then used in the description of the application of ensemble-based techniques to the case study of fault diagnosis of a diesel engine.

AAAI Conference 1986 Conference Paper

Mixing Binary and Continuous Connection Schemes for Knowledge Access

• Noel E. Sharkey

We present BACAS, a Binary and Continuous Activation System which is a parallel process content-addressable memory model. BACAS is designed for the representation and retrieval of "knowledge of the world" for automatic natural language understanding. In its present form, BACAS is a two-layered system with 10 K-structures (like scripts) in the binary output macro-layer represented by 46 Threshold Knowledge Units and 184 processing elements (like action events) in the continuous activation micro-layer. We discuss the problems of combining two types of connection system and describe a simulation in which the system moves from one pattern to the next in response to external input. A new tool for connection systems, the pulse-out, is introduced. This is a device which replaces the Boltzmann Machine in creating energy leaps. The pulse-out also has the advantage, in the current system, of setting the state of the system a short Hamming distance from an appropriate pattern.