Manifold-Based Inference for a Supervised Gaussian Process Classifier

One of the challenging classification problems consists of learning relevant and meaningful relationships between high dimensional representations across a relatively few observed individuals. Since this problem could have drastic effects on the classification performance, we propose a Bayesian alternative in the case of logistic regression. The proposed method has the additional benefit to learn both the adaptive embedding, as a Gaussian process, and the dimensionality reduction, jointly within the same Bayesian framework. We illustrate the efficiency and the accuracy of our framework for classifying images of manufacturing defects.