相关实验视频
Updated: Jun 19, 2026
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
8.9K
培训的不对称估计器封装深光子神经网络
Yizhi Wang1, Minjia Chen1, Chunhui Yao1,2
1Centre for Photonic Systems, Electrical Engineering Division, Department of Engineering, University of Cambridge, Cambridge, UK.
Nature communications
|March 3, 2025
概括
在光子神经网络 (PNN) 中的训练挑战是通过非对称训练 (AsyT) 来解决的. 这种方法通过在模拟光子领域保存信号,实现高效的深度PNN (DPNN),克服了传统反向传播的局限性.
科学领域:
- 光子学 是一个光子学.
- 人工智能的人工智能
- 神经网络的神经网络的神经网络
背景情况:
- 光子神经网络 (PNN) 提供高速,高带宽的计算,但由于设备的变化和需要大量资源,面临训练挑战.
- 现有的PNN反向传播 (BP) 方法通常需要精确的中间状态提取或显著的计算能力,阻碍了深度PNN (DPNN) 的效率和增加成本.
研究的目的:
- 为封装深光子神经网络 (DPNN) 引入一种新的轻量级训练方法.
- 通过在整个网络中保存模拟光子信号,使DPNNs的高效和强大的训练成为可能.
主要方法:
- 开发了非对称训练 (AsyT),这是一种针对封装DPNN量身定制的方法.
- 实现了AsyT,以最大限度地减少信号读取,并在DPNN结构中保持模拟光子信号完整性.
主要成果:
- AsyT为DPNNs提供了一个轻量级的解决方案,具有最小的读数,快速,节能运行,以及减少系统足迹.
- 在集成光子芯片上使用AsyT证明了封装DPNN的可重复性性能提升,在各种网络结构和数据集中优于in-silico BP.
- AsyT表现出操作方便,容错性和通用性,在各种场景中促进PNN加速,尽管制造变化.
结论:
- 非对称训练 (AsyT) 是训练深光子神经网络 (DPNN) 的有效和高效方法.
- AsyT克服了PNN中传统BP方法的局限性,为PNN加速提供了一种实用的方法.
- 开发的方法通过解决培训复杂性和提高绩效稳定性,促进PNN的更广泛采用.
相关概念视频
01:15Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT) is an advanced Nuclear Magnetic Resonance (NMR) technique specifically designed to detect and enhance the signals of low-abundance nuclei, such as carbon-13 and nitrogen-15, in small molecules. The fundamental principle behind INEPT is the transfer of polarization from a more abundant and highly polarizable nucleus, typically hydrogen-1, to the low-abundance nucleus of interest. This process effectively boosts the NMR signal of the...
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...