2026-09-20T11:52:48Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/115372 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Ochoa, Idoia 2022-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms The student, Mohit Goyal, accepted the attached license on 2022-04-06 at 11:09. The student, Mohit Goyal, submitted this Thesis for approval on 2022-04-06 at 11:14. This Thesis was approved for publication on 2022-04-07 at 11:56. DSpace SAF Submission Ingestion Package generated from Vireo submission #17596 on 2022-11-11 at 13:04:51 General-purpose compression for sequential data using recurrent neural networks Goyal, Mohit 2022-04-07 General-purpose Compression Neural Networks We consider lossless compression based on statistical data modeling followed by prediction-based encoding, where an accurate statistical model for the input data leads to substantial improvements in compression. We propose DZip, a general-purpose compressor for sequential data that exploits the well-known modeling capabilities of neural networks (NNs) for prediction, followed by arithmetic coding. DZip uses a novel hybrid architecture based on adaptive and semi-adaptive training. Unlike most NN-based compressors, DZip does not require additional training data and is not restricted to specific data types. The proposed compressor outperforms general-purpose compressors such as Gzip (29% size reduction on average) and 7zip (12% size reduction on average) on a variety of real datasets, achieves near-optimal compression on synthetic datasets, and performs close to specialized compressors for large sequence lengths, without any human input. While the main limitation of NN-based compressors is generally the encoding/decoding speed, we empirically demonstrate that DZip achieves comparable compression ratio to other NN-based compressors while being several times faster. Thesis eng https://hdl.handle.net/2142/115372 Copyright 2022 Mohit Goyal M.S. Thesis Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng