Fast Text Compression Using Artificial Neural Networks
Fast Text Compression Using Artificial Neural Networks
复制标题
使用人工神经网络进行快速文本压缩
DOI：
10.1007/978-1-4471-0123-9_44
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
A. Dinesh
中科院分区：
文献类型：
--
作者：
M. Sriram;A. Dinesh
神经网络有潜力将数据压缩算法扩展到目前使用的字符级n-gram模型之外，但通常被避免，因为它们太慢而不实用。我们介绍了一种模型，它比流行的Limply-Xiv压缩器（zip，zip，compress）产生更好的压缩，并且在时间，空间和压缩比方面与PPM和Burrows-Wheeler算法（目前最知名的算法）具有竞争力。压缩器是一种使用2层4 × 106 x1网络的比特级预测算术编码器，速度快（约104字符/秒），因为只有4-5个连接同时活动，并且因为它使用针对一遍训练优化的可变学习率。
Neural networks have the potential to extend data compression algorithms beyond the character level n-gram models now in use, but have usually been avoided because they are too slow to be practical. We introduce a model that produces better compression than popular Limply-Xiv compressors (zip, zip, compress), and is competitive in time, space, and compression ratio with PPM and Burrows-Wheeler algorithms, currently the best known. The compressor, a bit-level predictive arithmetic encoder using a 2 layer, 4 × 106by 1 network, is fast (about 104characters/second) because only 4–5 connections are simultaneously active and because it uses a variable learning rate optimized for one-pass training.