activity
20172020
most citedHigh performance ultra-low-precision convolutions on mobile devices

19 citations · 24 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG2020

Mixed-Precision Embedding Using a Cache

Jie Amy Yang, Jianyu Huang, Jongsoo Park +2

In recommendation systems, practitioners observed that increase in the number of embedding tables and their sizes often leads to significant improvement in model performances. Give…

cs.CV20195 cited

Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition

Bing Xu, Andrew Tulloch, Yunpeng Chen +2

We propose a new building block, IdleBlock, which naturally prunes connections within the block. To fully utilize the IdleBlock we break the tradition of monotonic design in state-…

cs.LG2018

Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

Jongsoo Park, Maxim Naumov, Protonu Basu +25

The application of deep learning techniques resulted in remarkable improvement of machine learning models. In this paper provides detailed characterizations of deep learning models…

cs.LG2018

On Periodic Functions as Regularizers for Quantization of Neural Networks

Maxim Naumov, Utku Diril, Jongsoo Park +3

Deep learning models have been successfully used in computer vision and many other fields. We propose an unorthodox algorithm for performing quantization of the model parameters. I…

cs.LG201719 cited

High performance ultra-low-precision convolutions on mobile devices

Andrew Tulloch, Yangqing Jia

Many applications of mobile deep learning, especially real-time computer vision workloads, are constrained by computation power. This is particularly true for workloads running on…