Sequential neural text compression

Jürgen Schmidhuber; Stefan Heil

doi:10.1109/72.478398

Sequential neural text compression

Jürgen Schmidhuber, Stefan Heil

Research output: Contribution to journal › Article › peer-review

56 Scopus citations

Abstract

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 language	English (US)
Pages (from-to)	142-146
Number of pages	5
Journal	IEEE Transactions on Neural Networks
Volume	7
Issue number	1
DOIs	https://doi.org/10.1109/72.478398
State	Published - Dec 1 1996
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14

ASJC Scopus subject areas

Artificial Intelligence
Software
Computer Networks and Communications
Computer Science Applications

Access to Document

10.1109/72.478398

Cite this

@article{d5ce27f0e95949dba8832dc9e3bb44c9,

title = "Sequential neural text compression",

abstract = "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. {\textcopyright} 1996 IEEE.",

author = "J{\"u}rgen Schmidhuber and Stefan Heil",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "1996",

month = dec,

day = "1",

doi = "10.1109/72.478398",

language = "English (US)",

volume = "7",

pages = "142--146",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "IEEE Computational Intelligence Society",

number = "1",

}

TY - JOUR

T1 - Sequential neural text compression

AU - Schmidhuber, Jürgen

AU - Heil, Stefan

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 1996/12/1

Y1 - 1996/12/1

N2 - 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.

AB - 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.

UR - http://ieeexplore.ieee.org/document/478398/

UR - http://www.scopus.com/inward/record.url?scp=0029732478&partnerID=8YFLogxK

U2 - 10.1109/72.478398

DO - 10.1109/72.478398

M3 - Article

SN - 1045-9227

VL - 7

SP - 142

EP - 146

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 1

ER -

Sequential neural text compression

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this