activity
20192022
most citedHardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer

12 citations · 12 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CL2022

Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT

Siyuan Lu, Chenchen Zhou, Keli Xie +2

With the development of deep learning and Transformer-based pre-trained models like BERT, the accuracy of many NLP tasks has been dramatically improved. However, the large number o…

cs.CL2021

Elbert: Fast Albert with Confidence-Window Based Early Exit

Keli Xie, Siyuan Lu, Meiqi Wang +1

Despite the great success in Natural Language Processing (NLP) area, large pre-trained language models like BERT are not well-suited for resource-constrained or real-time applicati…

eess.SP202012 cited

Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer

Siyuan Lu, Meiqi Wang, Shuang Liang +2

Designing hardware accelerators for deep neural networks (DNNs) has been much desired. Nonetheless, most of these existing accelerators are built for either convolutional neural ne…

cs.LG2019

Training Deep Neural Networks Using Posit Number System

Jinming Lu, Siyuan Lu, Zhisheng Wang +4

With the increasing size of Deep Neural Network (DNN) models, the high memory space requirements and computational complexity have become an obstacle for efficient DNN implementati…

eess.SP2019

A Hardware-Oriented and Memory-Efficient Method for CTC Decoding

Siyuan Lu, Jinming Lu, Jun Lin +1

The Connectionist Temporal Classification (CTC) has achieved great success in sequence to sequence analysis tasks such as automatic speech recognition (ASR) and scene text recognit…