可编程的基于素的全光学深度神经网络
Ting Yu Teo1, Xiaoxuan Ma2, Ernest Pastor3
1Singapore University of Technology and Design, 8 Somapah Road, Singapore 487372, Singapore.
Nanophotonics (Berlin, Germany)
|December 5, 2024
概括
本研究介绍了一种全光学感知器,用于超快速神经网络操作,采用化物材料. 该设备使用非线性激活功能,用于超过1GHz的高速,节能光学分类.
科学领域:
- 光子学和光学工程的工程.
- 材料科学 材料科学 材料科学
- 人工智能 硬件 硬件
背景情况:
- 全光计算为高速信息处理提供了潜力.
- 开发高效的非线性光学材料对于全光学神经网络至关重要.
- 现有技术在速度和能源效率方面面临限制.
研究的目的:
- 为了展示一个被动的全化物全光学感知器.
- 为了利用Ge2Sb2Te5的非线性反应来实现非线性激活函数 (NLAF).
- 为了实现高速,节能全光学神经分类.
主要方法:
- 在1500 nm时测量了Ge2Sb2Te5的分皮秒时间分辨率光学常量.
- 为全光学NLAF设计了一个Ge2Sb2Te5调的微波振器.
- 采用AlN作为波导材料,以有效散热.
- 用过的Sb2S3调整的Mach Zehnder干扰仪 (MZIs) 用于非挥发性物质.
- 用三层深度神经网络模型测试了该方案.
主要成果:
- 实现了西格形NLAF响应,其动态范围为-9.7dB.
- 通过两种温度分析,确定NLAF运行速度在纳秒范围内.
- 在深度神经网络中获得了94.5%的最大训练精度.
- 证明了高能效的全光学神经分类在速率> 1 GHz.
结论:
- 开发的全光学感知子方案对于高性能计算是可行的.
- 将Sb2S3编程的MZI重量与Ge2Sb2Te5的非线性响应结合起来,可以实现高效的光神经分类.
- 这种方法为下一代光学神经网络铺平了道路.
相关概念视频
01:18Imaging Biological Samples with Optical Microscopy
Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
01:25Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...