In this paper we describe the application of mixtures of experts on gender and ethnic classification of human faces, and pose classification, and show their feasibility on the FERET database of facial images. The FERET database allows us to demonstrate performance on hundreds or thousands of images. The mixture of experts is implemented using the "divide and conquer" modularity principle with respect to the granularity and/or the locality of information. The mixture of experts consists of ensembles of radial basis functions (RBFs). Inductive decision trees (DTs) and support vector machines (SVMs) implement the "gating network" components for deciding which of the experts should be used to determine the classification output and to restrict the support of the input space. Both the ensemble of RBF's (ERBF) and SVM use the RBF kernel ("expert") for gating the inputs. Our experimental results yield an average accuracy rate of 96% on gender classification and 92% on ethnic classification using the ERBF/DT approach from frontal face images, while the SVM yield 100% on pose classification.

A new descriptor of molecular structure, EVA, for use in the derivation of robustly predictive QSAR relationships is described. It is based on theoretically derived normal coordinate frequencies, and has been used extensively and successfully in proprietary chemical discovery programmes within Shell Research. As a result of informal dissemination of the methodology, it is now being used successfully in related areas such as pharmaceutical drug discovery. Much of the experimental data used in development remain proprietary, and are not available for publication. This paper describes the method and illustrates its application to the calculation of nonproprietary data, log P(ow), in both explanatory and predictive modes. It will be followed by other publications illustrating its application to a range of data derived from biological systems.

No abstract