We consider the task of assembling a large number of self controlled parts (or robots) into copies of a prescribed assembly (or formation). In particular, we introduce a way to sy...
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 mod...
William Power, Ray J. Frank, D. John Done, Neil Da...
We provide a category theoretic reformulation of control structures, which avoids explicit reference to names. The basis of the formulation is what we call a binding structure, wh...
Motivated by the slow learning properties of multilayer perceptrons (MLPs) which utilize computationally intensive training algorithms, such as the backpropagation learning algorit...
Abstract Features computed as statistics (e.g. histograms) of local filter responses have been reported as the most powerful descriptors for texture classification and segmentation...