Analysis-by-Synthesis by Learning to Invert Generative Black Boxes

For learning meaningful representations of data, a rich source of prior knowledge may come in the form of a generative black box, e.g. a graphics program that generates realistic facial images. We consider the problem of learning the inverseof a given generative model from data. The problem is non-trivial because it is difficult to create labelled training cases by hand, and the generative mapping is a black box in the sense that there is no analytic expression for its gradient. We describe a way of training a feedforward neural network that starts with just one labelled training example and uses the generative black box to "breed" more training data. As learning proceeds, the training set evolves and the labels that the network assigns to unlabelled training data converge to their correct values. We demonstrate our approach by learning to invert a generative model of eyes and an active appearance model of faces.