43

Lossless Data Compression with Neural Networks

 5 years ago
source link: https://www.tuicool.com/articles/hit/rUfq6nz
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

NNCP: Lossless Data Compression with Neural Networks

NNCP is an experiment to build a practical lossless data compressor with neural networks. The best performer uses an LSTM

model. A model based on self-attention (Transformer) is also evaluated.

The algorithms and results are described in thispaper.

NNCP is based on the LibNC library which allows fast and deterministic evaluation and training of neural networks on x86 CPUs. It is optimized for small batch sizes and low latency. LibNC has no dependency on other libraries and has a C API.

Compression ratio

Result for enwik8 :

Program

Compr. size

(bytes)

Ratio

(bpb)

gzip 36 445 248 2.92 xz 24 865 244 1.99 NNCP 16 924 569 1.35 CMIX (v17) 14 877 373 1.19

Result for enwik9 :

Program

Compr. size

(bytes)

Ratio

(bpb)

gzip 322 591 995 2.58 xz 197 331 816 1.58 NNCP 128 292 351 1.03 CMIX (v17) 116 394 271 0.93

Download

Linux version: nncp-2019-03-30.tar.gz . LibNC is currently only provided as object code.

Fabrice Bellard -


report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK