Highly Efficient Neural Network Language Model Compression Using Soft Binarization Training - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Rao Ma, Qi Liu, Kai Yu 0004. Highly Efficient Neural Network Language Model Compression Using Soft Binarization Training. In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019. pages 62-69, IEEE, 2019. [doi]

The following publications are possibly variants of this publication:

Neural Network Language Model Compression With Product Quantization and Soft BinarizationKai Yu 0004, Rao Ma, Kaiyu Shi, Qi Liu. taslp, 28:2438-2449, 2020. [doi]

A Highly Efficient Training-Aware Convolutional Neural Network Compression ParadigmChang Liu, Hongtao Lu. icmcs 2020: 1-6 [doi]

runs on WebDSL