Search
Now showing items 1-10 of 11
A comparative analysis of high performance associative memory models.
(2000)
Three variants of the Hopfield network are examined, each of which is trained using a different iterative approximation of the pseudo-inverse rule. All three variants are known to have significantly higher memory capacity ...
Design and use of neural network applications in telecommunications
(CRC Press, 2000)
This chapter describes the use of neural networks in the analysis of software systems. The development of large software systems over long periods of time, and the software crisis that this has produced, provides a rich ...
Optimising a neural tree classifier using a genetic algorithm
(2000)
This paper documents experiments performed using a GA to optimise the parameters of a dynamic neural tree model. Two fitness functions were created from two selected clustering measures, and a population of genotypes, ...
The analysis of animate object motion using neural networks and snakes
(2000)
This paper presents a mechanism for analysing the deformable shape of an object as it moves across the visual field. An object’s outline is detected using active contour models, and is then re-represented as shape, location ...
High performance associative memory models and symmetric connections
(2000)
Two existing high capacity training rules for the standard Hopfield architecture associative memory are examined. Both rules, based on the perceptron learning rule produce asymmetric weight matrices, for which the simple ...
Connectionist modelling of skill development : object balancing in young children
(Universal Press, 2000)
Input window size and neural network predictors
(Institute of Electrical and Electronics Engineers (IEEE), 2000)
Neural network approaches to time series prediction are briefly discussed, and the need to specify an appropriately sized input window identified. Relevant theoretical results from dynamic systems theory are briefly ...
Analysis of human motion using snakes and neural networks
(2000)
A novel technique is described for analysing human movement in outdoor scenes. Following initial detection of the humans using active contour models, the contours are then re-represented as normalised axis crossover vectors. ...
The Architecture and Performance of a Stochastic Competitive Evolutionary Neural Tree Network
(2000)
A new dynamic tree structured network - the Stochastic Competitive Evolutionary Neural Tree (SCENT) is introduced. The network is able to provide a hierarchical classification of unlabelled data sets. The main advantage ...