Tangent Prop - A formalism for specifying selected invariances in an adaptive network

Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)

Bibtex Metadata Paper

Authors

Patrice Simard, Bernard Victorri, Yann LeCun, John Denker

Abstract

In many machine learning applications, one has access, not only to training data, but also to some high-level a priori knowledge about the desired be(cid:173) havior of the system. For example, it is known in advance that the output of a character recognizer should be invariant with respect to small spa(cid:173) tial distortions of the input images (translations, rotations, scale changes, etcetera). We have implemented a scheme that allows a network to learn the deriva(cid:173) tive of its outputs with respect to distortion operators of our choosing. This not only reduces the learning time and the amount of training data, but also provides a powerful language for specifying what generalizations we wish the network to perform.