Learn More
SUMMARY A multilayer perceptron is usually considered a passive learner that only receives given training data. However, if a multilayer perceptron actively gathers training data that resolve its uncertainty about a problem being learnt, sufficiently accurate classification is attained with fewer training data. Recently, such active learning has been(More)
SUMMARY We propose a learning algorithm for self-organizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions. key words: competitive(More)
In this paper, we propose an efficient method for tracking multiple objects, which deals with occlusion situations in an image. We use Shape from silhouettes method to reconstruct objects 3D position from images taken from different directions. Then we track the ob-jects' reconstructed 3D positions by using mixed-state CONDENSATION algorithm. The(More)
  • 1