Narrow Results

The ad hoc nature of the clustering methods makes simulated data paramount in assessing the performance of clustering methods. Real datasets could be used in the evaluation of clustering methods with the major drawback of missing the assessment of many test scenarios. In this paper, we propose a formal quantification of component overlap. This quantification is derived from a set of theorems which allow us to derive an automatic method for artificial data generation. We also derive a method to estimate parameters of existing models and to evaluate the results of other approaches. Automatic estimation of the overlap rate can also be used as an unsupervised learning approach in data mining to determine the parameters of mixture models from actual observations.

This paper is an exploration of a straightforward but powerful unsupervised artificial neural network technique for the efficient coding of artificial and real data. Using an energy function based on the Rectified Gaussian distribution, we derive a neural architecture based on an unsupervised negative feedback network with fixed lateral connections. We show that, not only can this network identify local correlated structure in visual data but through the use of appropriate lateral connections, we can obtain a grouping of similar causes on the output response of the network. We show that the network may be used to form local spatiotemporal filters in response to real images contained in video. The shape of these filters reflects the nature of the video sequences.