Mathematics of Neural Networks. Models, Algorithms and Applications

Description

Springer, 1997. — 423 p. — ISBN 978-1-4613-7794-8.This volume of research papers comprises the proceedings of the first International Conference on Mathematics of Neural Networks and Applications (MANNA), which was held at Lady Margaret Hall, Oxford from July 3rd to 7th, 1995 and attended by 116 people. The meeting was strongly supported and, in addition to a stimulating academic programme, it featured a delightful venue, excellent food and accommodation, a full social programme and fine weather - all of which made for a very enjoyable week.PrefaceInvited papersN. M. Allinson and A. R. Kolcz N-tuple neural networksShun-ichi Amari Information geometry of neural networks -an overview15George Cybenko, Robert Gray and Katsuhiro Moizumi Q-learning: A tutorial and extensionsStephen Grossberg Are there universal principles of brain computation?Morris W. Hirsch On-line training of memory-driven attractor networksJ. G. Taylor Mathematical problems arising from constructing an artificial brainSubmitted papersJ. R. Alexander Jr. and J. P. Coughlin the successful use of probability data in connectionist modelsP. Edgar An Weighted mixture of models for on-line learningI. J. Anderson Local modifications to radial basis networksE.D. Aved'yan, M. Brown and C.J. Harris A statistical analysis of the modified nlms rulesDavid Barber, Peter Sollich and David Saad Finite size effects in on-line learning of multi-layer neural networksV. Beiu Constant fan-in digital neural networks are vlsi-optimalN. Benjathapanun, W. J. O. Boyle and K. T. V. Grattan The application of binary encoded 2nd differential spectrometry in preprocessing of uv -vis absorption spectral dataJan van den Berg and Jock H. Geselschap A non-equidistant elastic net algorithmMonica Bianchini, Stefano Fanelli, Marco Gori and Marco Protasi Unimodal loading problemsJan C. Bioch, Robert Carsouw and Rob Potharst On the use of simple classifiers for the initialisation of one-hiddenlayer neural netsChristopher M Bishop and Ian T Nabney Modelling conditional probability distributions for periodic variablesPaul C. Bressloff Integro-differential equations in compartmental model neurodynamicsSusan Brittain and Linda M. Haines Nonlinear models for neural networksMarco Budinich and Barbara Rosario A Neural network for the travelling salesman problem with a well behaved energy functionEnrico Capobianco Semiparametric artificial neural networksD.K. Y. Chiu, D. Bockus and J. Bradford An event-space feedforward network using maximum entropy partitioning with application to low level speech dataE.S. Chng, B. Mulgrew, S. Chen and G. Gibson Approximating the bayesian decision boundary for channel equalisation using subset radial basis function networkCarol G. Crawford Applications of graph theory to the design of neural networks for automated fingerprint identificationA. Delgado, C. Kambhampati and K. Warwick Zero dynamics and relative degree of dynamic recurrent neural networksAndrzej Dzielinski and Rafal Zbikowski Irregular sampling approach to neurocontrol: the band-and space-limited functions questionsMichael Eisele Unsupervised learning of temporal constancies by pyramidal-type neuronsS. W. Ellacott and A. Easdown Numerical aspects of machine learning in artificial neural networksAlistair Ferguson, Laurence C Dixon and Hamid Bolouri Learning algorithms for ram-based neural networksRichard Filer and James Austin Analysis of correlation matrix memory and partial matchimplications for cognitive psychologyJason A.S. Freeman and David Saad Regularization and realizability in radial basis function networksD. Husmeier, D. Allen and J. G. Taylor A universal approximator network for learning conditional probability densitiesMark P. Joy Convergence of a class of neural networksS. K. Asderidis and J. G. Taylor Applications of the compartmental model neuron to time series analysisJim Kay Information theoretic neural networks for contextually guided unsupervised learningPetri K. Oistinen Convergence in noisy trainingBarl Krekelberg and John G. Taylor Non-linear learning dynamics with a diffusing messengerAbderrahim Labbi A Variational approach to associative memoryBao-Liang Lu and Koji Ito Transformation of nonlinear programming problems into separable ones using multilayer neural networksS. P. Luttrell A theory of self-organising neural networksG.D. Magoulas, M.N. Vrahatis, T.N. Grapsa and G.S. Androulakis Neural network supervised training based on a dimension reducing methodG.D. Magoulas, M.N. Vrahatis, T.N. Grapsa and G.S. Androulakis A training method for discrete multilayer neural networksS. Manchanda and G.G.R. Green Local minimal realisations of trained hopfield networksGlenn Marion and David Saad Data dependent hyperparameter assignmentJ. C. Mason, 1. J. Anderson, G. Rodriguez and S. Seatzu Training radial basis function networks by using separable and orthogonalized gaussiansRonny Meir and Assaf J. Zeevi Error bounds for density estimation by mixturesH. N. Mhaskar On smooth activation functionsChristophe Molina and Mahesan Niranjan Generalisation and regularisation by gaussian filter convolution of radial basis function networksYves Moreau and Joos Vandewalle Dynamical system prediction: a lie algebraic approach for a novel neural architectureToru Ohira and Jack D. Cowan Stochastic neurodynamics and the system size expansionCazhaow S. Qazaz, Christopher K. I. Williams and Christopher M. Bishop An upper bound on the bayesian error bars for generalized linear regressionPeter Rieper, Sabine Kroner and Reinhard Moratz Capacity bounds for structured neural network architecturesDavid Saad and Sara A. Solla On-line learning in multilayer neural networksM. Samuelides, B. Doyon, B. Cessac and M. Quoy Spontaneous dynamics and associative learning in an assymetric recurrent random neural networkJonathan L. Shapiro, Adam Prugel-Bennett and Magnus Rattray A statistical mechanics analysis of genetic algorithms for search and learningSergey A. Shumsky Volumes of attraction basins in randomly connected boolean networksA. Shustorovich Evidential rejection strategy for neural network classifiersJ. Smid and P. Volf Dynamics approximation and change point retrieval from a neural network modelPeter Sollich Query learning for maximum information gain in a multi-layer neural networkDavid McG. Squire and Terry M. Caelli Shift, rotation and scale invariant signatures for two-dimensional contours, in a neural network architectureShin Suzuki Function approximation by threelayer artificial neural networksG. Tambouratzis, T. Tambouratzis and D. Tambouratzis Neural network versus statistical clustering techniques: A pilot study in a phoneme recognition taskG. L. Tarr, X. Clastres, L. Freyss, M. Samuelides, C. Dehainaut and W. Burckel Multispectral image analysis using pulsed coupled neural networksRua-Huan R. Tsaih Reasoning neural networksAnsgar H. L. West and David Saad Capacity of the upstart algorithmChristopher K. 1. Williams Regression with gaussian processesLi-Qun Xu Stochastic forward-perturbation, error surface and progressive learning in neural networksHoward Hua Yang Dynamical stability of a highdimensional self-organizing mapHuaiyu Zhu and Richard Rohwer Measurements of generalisation based on information geometryR. Zimmer Towards an algebraic theory of neural networks: Sequential composition