Lossless data compression methods based on neural network

Abstract

No lossless data compression method based on neural network has been found before. A lossless compression method based on BP network for the long character-string of 0 and 1 is given by establishing specific mapping Y and specific integer function and with the non-linear approximation capability of concrete three-layer BP network in this paper. The compression and decompression algorithms of the lossless compression method are provided. Experiments show that the compression ratio of the lossless compression method is usually around 16/11 and the method can effectively compress the data which have been compressed by Huffman coding, arithmetic coding or dictionary coding.