Search
Now showing items 1-9 of 9
The capacity and attractor basins of associative memory models
(1999)
The performance characteristics of five variants of the Hopfield network are examined. Two performance metrics are used: memory capacity, and a measure of the size of basins of attraction. We find that the posttraining ...
A modular attractor model of semantic access
(1999)
This paper presents results from lesion experiments on a modular attractor neural network model of semantic access. Real picture data forms the basis of perceptual input to the model. An ultrametric attractor space is used ...
A reward driven connectionist model of cognitive development
(1999)
Children learn many skills under self-supervision where exemplars of target responses are not available. Connectionist models which rely on supervised learning are therefore not appropriate for modelling all forms of ...
Human shape recognition from snakes using neural networks
(Institute of Electrical and Electronics Engineers (IEEE), 1999)
This paper documents experiments which have been carried out with several neural network systems designed to categorise pedestrian shapes from non-pedestrian shapes. Active Contour models (‘Snakes’) [1] have been used to ...
Detecting partial occlusion of humans using snakes and neural networks
(1999)
This paper summarises the development of a computer system designed to detect moving humans in an image or series of images. The system combines the use of active contour models, ‘snakes’, which detect human objects in an ...
Time series prediction and neural networks
(1999)
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 introduced, ...
Applications of neural networks to telecommunications systems
(ELITE Foundation, 1999)
This paper gives an overview of a project involving the application of neural networks to Telecommunications Systems. Five application areas are discussed, including cloned software identification and the detection of ...
An investigation into Karmilov-Smith's RR model : the effects of structured tuition
(1999)
Karmiloff-Smith's model of representational redescription describes development proceeding from implicit to explicit knowledge. During part of this process, knowledge is said to be resistant to external influences. However, ...
Hierarchical Classification with a Competitive Evolutionary Neural Tree
(1999)
A new, dynamic, tree structured network, the Competitive Evolutionary Neural Tree (CENT) is introduced. The network is able to provide a hierarchical classification of unlabelled data sets. The main advantage that the CENT ...