Predictive Coding with Neural Nets: Application to Text Compression

Part of Advances in Neural Information Processing Systems 7 (NIPS 1994)

Bibtex Metadata Paper

Authors

Jürgen Schmidhuber, Stefan Heil

Abstract

To compress text files, a neural predictor network P is used to ap(cid:173) proximate the conditional probability distribution of possible "next characters", given n previous characters. P's outputs are fed into standard coding algorithms that generate short codes for characters with high predicted probability and long codes for highly unpre(cid:173) dictable characters. Tested on short German newspaper articles, our method outperforms widely used Lempel-Ziv algorithms (used in UNIX functions such as "compress" and "gzip").