Dynamic Cell Structures (DCS) represent a family of artificial neural architectures suited both for unsupervised and supervised learning. They belong to the recently [Martinetz94] introduced class of Topology Representing Networks (TRN) which build perlectly topology preserving feature maps. DCS empI'oy a modified Kohonen learning rule in conjunction with competitive Hebbian learning. The Kohon...

Given the range of neural network paradigms available at the moment, we might ask why anyone would still want to use backpropagation. An important argument for using this learning algorithm seems to be its popularity. Backpropagation has become one of the standard technologies in connectionist modelling. Although it was invented by Werbos in 1974, it has only been with the publication of the so...

The matching forest problem in mixed graphs is a common generalization of the matching problem in undirected graphs and the branching problem in directed graphs. Giles presented an O(nm)-time algorithm for finding a maximum-weight matching forest, where n is the number of vertices and m is that of edges, and a linear system describing the matching forest polytope. Later, Schrijver proved total ...

with the explosive growth in amount of information, it is highly required to utilize tools and methods in order to search, filter and manage resources. one of the major problems in text classification relates to the high dimensional feature spaces. therefore, the main goal of text classification is to reduce the dimensionality of features space. there are many feature selection methods. however...

background: increasing frame rate is a challenging issue for better interpretation of medical images and diagnosis based on tracking the small transient motions of myocardium and valves in real time visualization. methods: in this paper, manifold learning algorithm is applied to extract the nonlinear embedded information about echocardiography images from the consecutive images in two dimension...

In this paper, we explore several machine learning techniques for classifying spoken language. In particular, we construct algorithms which utilize various spectral features derived from English and Mandarin Chinese phone call audio to predict the language to which the phone call belongs. We investigate multiple feature sets and modeling approaches, and find that Gaussian Mixture Models, combin...

In the last few years there have been a growing number of studies concerning the introduction of quaternions into neural networks, which demand a faster learning technique with superior performance. In this paper, we propose a fast, but novel quaternionic resilient propagation (H-RPROP) algorithm for high dimensional problems. It achieves significantly faster learning over quaternionic domain b...