no code implementations • 13 Jan 2020 • Seth H. Huang, Xu Lingjie, Jiang Congwei
We present a novel architecture, residual attention net (RAN), which merges a sequence architecture, universal transformer, and a computer vision architecture, residual net, with a high-way architecture for cross-domain sequence modeling.
no code implementations • 27 Nov 2018 • Wei Wei, Xu Lingjie, Jin Lingling, Zhang Wei, Zhang Tianjun
In this work, a synthetic benchmarks framework is firstly proposed to address the above drawbacks of AI benchmarks.