Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)
Thomas Dietterich, Ajay Jain, Richard Lathrop, Tomás Lozano-Pérez
In drug activity prediction (as in handwritten character recogni(cid:173) tion), the features extracted to describe a training example depend on the pose (location, orientation, etc.) of the example. In hand(cid:173) written character recognition, one of the best techniques for ad(cid:173) dressing this problem is the tangent distance method of Simard, LeCun and Denker (1993). Jain, et al. (1993a; 1993b) introduce a new technique-dynamic reposing-that also addresses this prob(cid:173) lem. Dynamic reposing iteratively learns a neural network and then reposes the examples in an effort to maximize the predicted out(cid:173) put values. New models are trained and new poses computed until models and poses converge. This paper compares dynamic reposing to the tangent distance method on the task of predicting the bio(cid:173) logical activity of musk compounds. In a 20-fold cross-validation,