尖峰神经网络
计算机科学
人工智能
原色
计算机视觉
波长
彩色视觉
Cone(正式语言)
Spike(软件开发)
感知
光学
物理
人工神经网络
神经科学
生物
算法
软件工程
作者
Qing Wan,Xiangjing Wang,Chunsheng Chen,Li Zhu,Kailu Shi,Baocheng Peng,Yixin Zhu,Huiwu Mao,Haotian Long,Shuo Ke,Chuanyu Fu,Ying Zhu,Changjin Wan
出处
期刊:Research Square - Research Square
日期:2022-11-23
标识
DOI:10.21203/rs.3.rs-2255181/v1
摘要
Abstract The cone photoreceptors in our eyes selectively transduce the natural light into spiking representations, which endows the brain with high energy-efficiency color vision. However, the cone-like device with color-selectivity and spike-encoding capability remains challenging. Here, we propose a vertical integrated spiking cone photoreceptor (VISCP) array with the structure of ITO/Ta2O5/Ag/IGZO/ITO, which can directly transduce persistent lights into spike trains at a certain rate according to the input wavelengths. The VISCPs have an ultralow power consumption of ≤400 pW per spike in visible light, which is very close to biological cones. In this work, lights with three wavelengths were exploited as pseudo three primary colors to form ‘colorful’ images for recognition tasks, and the device with the ability to discriminate mixed colors shows a better accuracy. Our results would enable hardware spiking neural networks with biologically plausible visual perception and provide great potential for the development of dynamic vision sensors.
科研通智能强力驱动
Strongly Powered by AbleSci AI