Search
Now showing items 11-20 of 20
Analysing Hierarchical Data Using a Stochastic Evolutionary Neural Tree
(1998)
SCENT is simple competitive neural network model that evolves a tree structured set of nodes in response to being presented with an unlabelled data set. The resulting set of weight vectors and their relationship can be ...
A neural network model of visual object recognition impairment after brain damage
(1998)
Dysfunction of the visual object recognition system in humans is briefly discussed and a basic connectionist model of visual object recognition is introduced. Experimentation in which two variants of this model are lesioned ...
An investigation into the performance and representation of a stochastic evolutionary neural tree
(Springer Nature, 1997)
The Stochastic Competitive Evolutionary Neural Tree (SCENT) is a new unsupervised neural net that dynamically evolves a representational structure in response to its training data. Uniquely SCENT requires no initial parameter ...
Traffic trends analysis using neural networks
(1997)
An application of time series prediction, to traffic forecasting in ATM networks, using neural nets is described. One key issue, the number of data points needed to be included in the input representation to the net is ...
Using neural networks to analyse software complexity
(University of Hertfordshire, 1995)
Units of software are represented as points in a multidimensional space, by calculating 12 measures of software complexity for each unit. To large sets of commercial software are thereby represented as 2236 and 4456 12-ary ...
The development of a software clone detector
(1995)
Cloning, the copying and modifying of blocks of code, is the most basic means of software reuse. Code cloning has been very extensively used within the software development design community. Unofficial surveys carried out ...
Dynamic competitive learning applied to the clone detection problem
(University of Hertfordshire, 1995)
A novel neural network architecture, 'Dynamic Competitive Learning', has been applied to the software clone detection problem in telecommunications systems. A software clone is a copy (subsequently modified), of a piece ...
The use of metrics in connectionist psychological models
(University of Hertfordshire, 1993)
Models of psychological and cognitive phenomena that are based on connectionist processing have recently been described. These include Norris's back propagation model, Schyns's model based on Kohonen nets and Hinton and ...