Predictive Coding with Neural Nets: Application to Text Compression
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").
Cite
Text
Schmidhuber and Heil. "Predictive Coding with Neural Nets: Application to Text Compression." Neural Information Processing Systems, 1994.Markdown
[Schmidhuber and Heil. "Predictive Coding with Neural Nets: Application to Text Compression." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/schmidhuber1994neurips-predictive/)BibTeX
@inproceedings{schmidhuber1994neurips-predictive,
title = {{Predictive Coding with Neural Nets: Application to Text Compression}},
author = {Schmidhuber, Jürgen and Heil, Stefan},
booktitle = {Neural Information Processing Systems},
year = {1994},
pages = {1047-1054},
url = {https://mlanthology.org/neurips/1994/schmidhuber1994neurips-predictive/}
}