Frank Fallside

Learn More
An analysis is made of the behavior of the Hopfield model as a content-addressable memory (CAM) and as a method of solving the traveling salesman problem (TSP). The analysis is based on the geometry of the subspace set up by the degenerate eigenvalues of the connection matrix. The dynamic equation is shown to be equivalent to a projection of the input(More)
The effect of the coefficients used in the conventional back propagation algorithm on training connectionist models is discussed, using a vowel recognition task in speech processing as an example. Some weaknesses of the use of fixed coefficients are described and an adaptive algorithm using variable coefficients is presented. This is found to be efficient(More)
This paper describes the research underway for the ESPRIT WERNICKE project. The project brings together a number of different groups from Europe and the US and focuses on extending the state-of-the-art for hybrid hidden Markov model/connectionist approaches to large vocabulary, continuous speech recognition. This paper describes the specific goals of the(More)
I Recent studies have shown that non-linear prediction can be implemented with neural networks, and non-linear predictors will on average achieve about 2 3 improvement in prediction gain over conventional linear predictors. In this paper, we take the advantage of non-linear prediction with neural network, apply it to predictive speech coding and attempt to(More)
Studies in the psychology of reading indicate that reading probably involves recognising features which are present in letters, such as loops, turns and straight strokes. If this is the case it is likely that recognising these features will be a useful technique for the machine recognition of cursive script. This paper describes a new method of detecting(More)
g…ihGpEsxpixqG„‚FTS g—m˜ridge …niversity ingineering hep—rtment „rumpington ƒtreet g—m˜ridge gfP I€ ingl—nd w—r™h IWWI e dire™t ™ontrol s™heme for — ™l—ss of ™ontinuous time nonline—r systems using neuE r—l networks is presentedF „he o˜je™tive of ™ontrol is to tr—™k — desired referen™e sign—lF „his o˜je™tive is —™hieved through inputGoutput line—riz—tion(More)
F. Fallside We develop a sequential adaptation algorithm for radial basis function (RBF) neural networks of Gaussian nodes, based on the method of successive F-Projections. This method makes use of each observation efficiently in that the network mapping function so obtained is consistent with that information and is also optimal in the least L 2-norm(More)