Showing papers by "Santanu Chaudhury published in 1994"
01 Mar 1994
TL;DR: A new neural network strategy for clustering that works on the histogram and is therefore faster than existing unsupervised learning networks and was applied to a wide class of problems including gray level image reduction, color segmentation and remotely sensed image segmentation.
Abstract: A new neural network strategy for clustering is presented. The network works on the histogram and the process is similar to mode separation. The number of clusters are autonomously detected by the network and it overcomes some major difficulties encountered by mode separation techniques. Clustering is done by first selecting the prototypes and then assigning patterns to one of the prototypes based on its distance from the prototype and the distribution of data. The network does not employ weight learning and is therefore faster than existing unsupervised learning networks. The network was applied to a wide class of problems including gray level image reduction, color segmentation and remotely sensed image segmentation. The experimental results obtained are promising. >
16 citations
TL;DR: A neural network based control scheme for robot tracking applications using Gaussian networks to model both the forward and the inverse dynamics of a robot arm.
6 citations