We propose a hierarchical, unsupervised clustering algorithm (TreeGCS) based upon the Growing Cell Structure (GCS) neural network of Fritzke. Our algorithm improves an inconsisten...
Abstract. In neural networks, network faults can be exhibited in different forms, such as node fault and weight fault. One kind of weight faults is due to the hardware or software ...
In the neural network literature, input feature de-correlation is often referred as one pre-processing technique used to improve the MLP training speed. However, in this paper, we...
We describe a system which is designed to assist animators in extracting high-level information from sequences of images. The system is not meant to replace animators, but to be a...
David P. Gibson, Neill W. Campbell, Colin J. Dalto...
We present a binocular robot that learns compensatory camera movements for image stabilization purposes. Most essential in achieving satisfactory image stabilization performance i...