概括
我们介绍了剩余光子神经网络 (Res-PNN) 架构,以训练更深层的网络. 光电快捷连接稳定训练,改善深度学习硬件加速.
科学领域:
- 光子学 是一个光子学.
- 深度学习 硬件加速 硬件加速
- 人工智能的人工智能
背景情况:
- 芯片上的光子神经网络 (PNN) 显示了深度学习的前景.
- 由于梯度消失/爆炸问题,训练更深层次的PNN具有挑战性.
- 现有的架构难以处理复杂的推理任务.
研究的目的:
- 提出一种新的芯片内深度残留光子神经网络 (Res-PNN) 架构.
- 为了使更深层次的PNN能够进行稳定的培训,以增强深度学习应用程序.
- 在PNN培训中解决梯度消失和爆炸问题.
主要方法:
- 开发了一个芯片上的Res-PNN架构,利用光电快捷连接.
- 使用功率分割器,波长解复器和光电探测器实现了快捷连接.
- 通过光学重量层促进了直接梯度反向传播路径.
主要成果:
- 在CIFAR-10上达到88.4%的分类准确度,在CIFAR-100上达到80.3%.
- 与完全连接的PNN相比,Res-PNN提高了CIFAR-10精度3.2%和CIFAR-100精度11.3%.
- 证明了更深层次的PNN的稳定训练,减轻了梯度问题.
结论:
- 拟议的Res-PNN架构有效地训练了更深层的光子神经网络.
- 光电快捷连接对于稳定的梯度传播和提高精度至关重要.
- 在深度学习中,Res-PNN为硬件加速提供了重大进步.
相关概念视频
Neural Circuits
1.0K
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...
1.0K
Anatomy of the Eyeball
5.9K
The eye is a spherical, hollow structure composed of three tissue layers. The outer layer — the fibrous tunic, comprises the sclera — a white structure — and the cornea, which is transparent. The sclera encompasses some of the ocular surface, most of which is not visible. However, the 'white of the eye' is distinctively visible in humans compared to other species. The cornea, a clear covering at the front of the eye, enables light penetration. The eye's middle...
5.9K


