no code implementations • 16 Sep 2022 • Chuanqing Wang, Chaoming Fang, Yong Zou, Jie Yang, Mohamad Sawan
In this paper, we propose an energy-efficient dynamic scenes processing framework (SpikeSEE) that combines a spike representation encoding technique and a bio-inspired spiking recurrent neural network (SRNN) model to achieve intelligent processing and extreme low-power computation for retinal prostheses.
no code implementations • 3 Sep 2019 • Ruqian Lu, Shengluan Hou, Chuanqing Wang, Yu Huang, Chaoqun Fei, Songmao Zhang
We have also shown that the knowledge based approach may be made more powerful by introducing grammar parsing and RST as inference engine.