Reverse TDNN: An Architecture For Trajectory Generation

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

Bibtex Metadata Paper

Authors

Patrice Simard, Yann Le Cun

Abstract

The backpropagation algorithm can be used for both recognition and gen(cid:173) eration of time trajectories. When used as a recognizer, it has been shown that the performance of a network can be greatly improved by adding structure to the architecture. The same is true in trajectory generation. In particular a new architecture corresponding to a "reversed" TDNN is proposed. Results show dramatic improvement of performance in the gen(cid:173) eration of hand-written characters. A combination of TDNN and reversed TDNN for compact encoding is also suggested.