We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Despite the decentralized and unorganized nature of the web, we show that the web self-organizes such that communities of highly related pages can be efficiently identified based purely on connectivity. This discovery allows the identification of communities independent of, and unbiased by, the specific words used by authors. Applications include improved search engines, content filtering, and objective analysis of relationships within and between communities on the web.

No abstract

Background-Urocortin is a novel cardioprotective agent that can protect cardiac myocytes from the damaging effects of ischemia/reperfusion both in culture and in the intact heart and is effective when given at reperfusion. Methods and Results-We have analyzed global changes in gene expression in cardiac myocytes after urocortin treatment using gene chip technology. We report that urocortin specifically induces enhanced expression of the Kir 6.1 cardiac potassium channel subunit. On the basis of this finding, we showed that the cardioprotective effect of urocortin both in isolated cardiac cells and in the intact heart is specifically blocked by both generalized and mitochondrial-specific K ATP channel blockers, whereas the cardioprotective effect of cardiotrophin-1 is unaffected. Conversely, inhibiting the Kir 6.1 channel subunit greatly enhances cardiac cell death after ischemia. Conclusions-This is, to our knowledge, the first report of the altered expression of a K ATP channel subunit induced by a cardioprotective agent and demonstrates that K ATP channel opening is essential for the effect of this novel cardioprotective agent.

No abstract