Training Deep Neural Networks Using Posit Number System

no code implementations • 6 Sep 2019 • Jinming Lu, Siyuan Lu, Zhisheng Wang, Chao Fang, Jun Lin, Zhongfeng Wang, Li Du

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 implementations.

Image Classification

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

no code implementations • 8 May 2019 • Siyuan Lu, Jinming Lu, Jun Lin, Zhongfeng Wang

Firstly, we improve the beam search decoding algorithm to save the storage space.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3