DeepSZ: A novel framework to compress deep neural networks by using error-bounded lossy compression
Today's deep neural networks (DNNs) are becoming deeper and wider because of
increasing demand on the analysis quality and more and more complex applications to …
increasing demand on the analysis quality and more and more complex applications to …
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
S Jin, S Di, X Liang, J Tian, D Tao… - arXiv preprint arXiv …, 2019 - arxiv.org
DNNs have been quickly and broadly exploited to improve the data analysis quality in many
complex science and engineering applications. Today's DNNs are becoming deeper and …
complex science and engineering applications. Today's DNNs are becoming deeper and …
[PDF][PDF] DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
S Jin, S Di, X Liang, J Tian, D Tao, F Cappello - 2019 - researchgate.net
Today's deep neural networks (DNNs) are becoming deeper and wider because of
increasing demand on the analysis quality and more and more complex applications to …
increasing demand on the analysis quality and more and more complex applications to …
DeepSZ: A novel framework to compress deep neural networks by using error-bounded lossy compression
S Jin, S Di, X Liang, J Tian, D Tao… - 28th ACM International …, 2019 - experts.illinois.edu
Today's deep neural networks (DNNs) are becoming deeper and wider because of
increasing demand on the analysis quality and more and more complex applications to …
increasing demand on the analysis quality and more and more complex applications to …
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
S Jin, S Di, X Liang, J Tian, D Tao… - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
DNNs have been quickly and broadly exploited to improve the data analysis quality in many
complex science and engineering applications. Today's DNNs are becoming deeper and …
complex science and engineering applications. Today's DNNs are becoming deeper and …
DeepSZ: A Novel Framework to Compress Deep Neural Networks by using Error-Bounded Lossy Compression
S Jin, S Di, X Liang, J Tian, D Tao, F Cappello - 2019 - scholarsmine.mst.edu
Today's deep neural networks (DNNs) are becoming deeper and wider because of
increasing demand on the analysis quality and more and more complex applications to …
increasing demand on the analysis quality and more and more complex applications to …
[PDF][PDF] DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
S Jin - 2019 - pdfs.semanticscholar.org
• Each data point's value is predicted based on its neighboring data points by an adaptive,
best-fit prediction method.• Each floating-point weight value is converted to an integer …
best-fit prediction method.• Each floating-point weight value is converted to an integer …
[PDF][PDF] DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
S Jin, S Di, X Liang, J Tian, D Tao, F Cappello - 2019 - researchgate.net
Today's deep neural networks (DNNs) are becoming deeper and wider because of
increasing demand on the analysis quality and more and more complex applications to …
increasing demand on the analysis quality and more and more complex applications to …