Sequential neural text compression

Jürgen Schmidhuber, Stefan Heil

Research output: Contribution to journalArticlepeer-review

51 Scopus citations


The purpose of this paper is to show that neural networks may be promising tools for data compression without loss of information. We combine predictive neural nets and statistical coding techniques to compress text files. We apply our methods to certain short newspaper articles and obtain compression ratios exceeding those of the widely used Lempel-Ziv algorithms (which build the basis of the UNIX functionscompressandgrip"). The main disadvantage of our methods is that they are about three orders of magnitude slower than standard methods. © 1996 IEEE.
Original languageEnglish (US)
Pages (from-to)142-146
Number of pages5
JournalIEEE Transactions on Neural Networks
Issue number1
StatePublished - Dec 1 1996
Externally publishedYes

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Computer Networks and Communications
  • Computer Science Applications


Dive into the research topics of 'Sequential neural text compression'. Together they form a unique fingerprint.

Cite this