Search
Now showing items 81-90 of 93
The Analysis of the addition of Stochasticity to a Neural Tree Classifier
(2001)
This paper describes various mechanisms for adding stochasticity to a dynamic hierarchical neural clusterer. Such a network grows a tree-structured neural classifier dynamically in response to the unlabelled data with which ...
High performance associative memory models and sign constraints
(2001)
The consequences of imposing a sign constraint on the standard Hopfield architecture associative memory model, trained using perceptron like learning rules, is examined. Such learning rules have been shown to have capacity ...
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 ...
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 ...
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. ...
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 ...
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 ...