An optical neural network using less than 1 photon per multiplication.
An optical neural network using less than 1 photon per multiplication.
复制标题
DOI：
10.1038/s41467-021-27774-8
复制
发表时间：
2022-01-10
影响因子：
16.6
通讯作者：
McMahon PL
中科院分区：
文献类型：
--
作者：
Wang T;Ma SY;Wright LG;Onodera T;Richard BC;McMahon PL
深度学习已成为科学和行业的宽度工具。深度学习。我们在实验中展示了基于光点产品的光学中性网络，该网络在手写数字分类中使用〜3.1的每个重量乘法的照片进行了99％的精度，并且使用〜2.5 x 10-10-90％的精度（〜2.5 x 10- 19 J的光能）每个重量乘法。我们的工作表明，光学神经网络可以使用极低的光能实现准确的结果。
尽管理论表明，基于光学基质 - 矢量乘数的高节能的光中性网络（ONN）是可能的，但在这里缺乏实验验证，但作者报告了使用<1 <1 scordon检测到的光子> 90％的ONN乘法。
Deep learning has become a widespread tool in both science and industry. However, continued progress is hampered by the rapid growth in energy costs of ever-larger deep neural networks. Optical neural networks provide a potential means to solve the energy-cost problem faced by deep learning. Here, we experimentally demonstrate an optical neural network based on optical dot products that achieves 99% accuracy on handwritten-digit classification using ~3.1 detected photons per weight multiplication and ~90% accuracy using ~0.66 photons (~2.5 × 10−19 J of optical energy) per weight multiplication. The fundamental principle enabling our sub-photon-per-multiplication demonstration—noise reduction from the accumulation of scalar multiplications in dot-product sums—is applicable to many different optical-neural-network architectures. Our work shows that optical neural networks can achieve accurate results using extremely low optical energies. Though theory suggests that highly energy efficient optical neural networks (ONNs) based on optical matrix-vector multipliers are possible, an experimental validation is lacking. Here, the authors report an ONN with >90% accuracy image classification using <1 detected photon per scalar multiplication.
登录
查看更多内容
可以自由扩展和可重新配置的光学硬件，用于深度学习。
影响因子：
4.6
作者：
Bernstein L;Sludds A;Hamerly R;Sze V;Emer J;Englund D
通讯作者：
Englund D
影响因子：
5.4
作者：
Park, Jeongwoo;Lee, Juyun;Jeon, Dongsuk
通讯作者：
Jeon, Dongsuk
影响因子：
10.4
作者：
Bueno, J.;Maktoobi, S.;Brunner, D.
通讯作者：
Brunner, D.
影响因子：
10.4
作者：
Matthes, Maxim E. W.;del Hougne, Philipp;Popoff, Sebastien M.
通讯作者：
Popoff, Sebastien M.
影响因子：
4.6
作者：
Chang J;Sitzmann V;Dun X;Heidrich W;Wetzstein G
通讯作者：
Wetzstein G