Titlebook: Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003; Joint International Okyay Kaynak,Ethem Alpaydin,Lei Xu C

Nerve-Block

Fast and Efficient Training of RBF Networkstic, iterative training algorithms (e.g. gradient-based or second-order techniques) or clustering methods in combination with a linear optimisation technique (e.g. c-means and singular value decomposition for a linear least-squares problem) are applied to find the parameters (centres, radii and weig

Carbon-Monoxide

CREST

Differential ICAation [2]. In this paper we present an ICA algorithm which employs differential learning, thus named as .. We derive a differential ICA algorithm in the framework of maximum likelihood estimation and random walk model. Algorithm derivation using the natural gradient and local stability analysis are

向外

欺騙世家

infantile

Optimal Hebbian Learning: A Probabilistic Point of Viewlearning rule from a probabilistic optimality criterion. Our approach allows us to obtain quantitative results in terms of a learning window. This is done by maximising a given likelihood function with respect to the synaptic weights. The resulting weight adaptation is compared with experimental res

Nonflammable

Competitive Learning by Information Maximization: Eliminating Dead Neurons in Competitive Learning the lateral inhibition is used. Instead, the new method is based upon mutual information maximization between input patterns and competitive units. In maximizing mutual information, the entropy of competitive units is increased as much as possible. This means that all competitive units must equally

斥責(zé)

Enzyme

Finite Mixture Model of Bounded Semi-naive Bayesian Networks Classifiershows a good performance in classification tasks. However, the traditional SNBs can only combine two attributes into a combined attribute. This inflexibility together with its strong independency assumption may generate inaccurate distributions for some datasets and thus may greatly restrict the cla

抵制