一个生物灵感的物质模拟光电子储存器计算,用于人类行动处理
Hangyuan Cui1, Yu Xiao2, Yang Yang1
1School of Electronic Science and Engineering, National Laboratory of Solid-State Microstructures, Nanjing University, Nanjing, 210023, P. R. China.
Nature communications
|March 6, 2025
概括
这项研究介绍了一种生物灵感的物质计算系统,用于动态视觉处理. 这种新的方法在显著降低能源消耗的情况下实现了高精度的运动识别,从而推进了神经形态电子.
科学领域:
- 神经形态工程的神经形态工程
- 计算机视觉 计算机视觉
- 材料科学 材料科学 材料科学
背景情况:
- 目前的计算机视觉系统是能源密集型和计算昂贵的.
- 将物理整合到生物启发系统中为能源效率提供了潜力,但也面临着处理挑战.
- 在使用生物启发方法的高效,现实世界的动态视觉处理中存在差距.
研究的目的:
- 开发一个生物灵感的物质模拟光电子储计算系统,用于动态视觉处理.
- 为了解决当前数据密集型计算机视觉的局限性.
- 在处理动态视觉信息时实现高能效和精度.
主要方法:
- 使用InGaZnO光电子突触晶体管作为储存器.
- 在输出层使用基于TaOX的memristor数组.
- 实施了受感场灵感的编码方案,用于简化特征提取.
主要成果:
- 在四个运动识别数据集上实现了高识别精度 (>90%).
- 成功验证了跌倒行为识别.
- 证明了每次操作的低能耗 (~45.78μJ),性能优于以前的人类操作处理方法.
结论:
- 开发的生物灵感的in-materia系统为节能动态视觉处理提供了一个有前途的途径.
- 这项工作为下一代计算机视觉应用推进了神经形态电子学.
- 该系统的效率和准确性凸显了将基于物理的计算与生物灵感设计相结合的潜力.
相关概念视频
Electrochemical Systems
Electrochemical systems provide a fascinating insight into the dynamic interplay of charged species within various phases. One notable example is the interaction between a membrane permeable to K⁺ ions but not to Cl⁻ ions, separating an aqueous KCl solution from pure water. As K⁺ ions diffuse through the membrane, they generate net charges on each phase, leading to a potential difference between them.Similarly, when a piece of Zn is immersed in an aqueous ZnSO₄ solution, the Zn metal, composed...
Parallel Processing
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...


