Publications

Pfeiffer, M & Leaney, J 1995, 'Simple reliable monitor: a formalisation of the concept of a safe software monitor', Australian Computer Journal, vol. 27, no. 1, pp. 9-15.
View description>>

The (safety) monitor concept is extended to the simple, reliable (SR) monitor which may be considered as an alternative to n-version programming. With the use of subtype and inheritance concepts, plus pre and post condition refinement, it is shown how the classes of monitors for problems can be set up.

Lister, R 1970, 'Error functions, error signals, and conjugate gradient back propagation', 4th International Conference on Artificial Neural Networks, 4th International Conference on Artificial Neural Networks, IEE, pp. 76-81.
View/Download from: Publisher's site
View description>>

We propose a three-class taxonomy of error functions, based on the limit behaviour of the error signal. We classify four established error functions: the quadratic, Fahlman's Quickprop, entropy, and the exception error function. We introduce two new error functions, and benchmark all six on the N-2-N encoder. The two new functions found correct solutions faster and more reliably than the established functions.

Lister, R & Stone, JV 1970, 'Empirical study of the time complexity of various error functions with conjugate gradient back propagation', IEEE International Conference on Neural Networks - Conference Proceedings, pp. 237-241.
View description>>

We describe an empirical comparison of the scaling behaviour of six error functions, on a conjugate gradient form of Back Propagation. We classify the functions according to the limit behaviours of their respective error signals, as the target value and the actual output value approach opposite extremes. These limit behaviours are zero limit, finite limit, and infinite limit. Despite such a wide divergence in their limit behaviours, we find that all six error functions exhibit a median run-time order of approximately O(N 4) on the N-2-N encoder. This result indicates that, while some factors affecting the scaling behaviour of standard and conjugate gradient Back Propagation have been previously identified (such as saturation), other factors remain unidentified.