Ternary Weight Networks

16 May 2016Fengfu LiBo ZhangBin Liu

We introduce ternary weight networks (TWNs) - neural networks with weights constrained to +1, 0 and -1. The Euclidian distance between full (float or double) precision weights and the ternary weights along with a scaling factor is minimized... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.