低深度光学神经网络
Low-Depth Optical Neural Networks
摘要:
光学神经网络(ONN)是一种新兴的机器学习应用的有吸引力的建议,使高速计算与低能耗。然而,在将ONN应用于工业应用时存在一些挑战,包括激活功能的实现和保持稳定性。具体地,ONN的稳定性随着电路深度而降低,限制了ONN在实际应用中的可扩展性。在这里,我们演示了如何压缩ONN的电路深度,使其仅按比例缩放,从而在噪声鲁棒性方面获得指数增益。我们的低深度(LD)ONN是基于一个架构,称为光学计算的点积单位(OCTOPUS),它也可以单独应用作为一个线性感知器解决分类问题。使用字母识别的标准数据集,我们提出了数值证据,表明与先前基于奇异值分解的ONN提案相比,LD-ONN可以在噪声鲁棒性方面表现出显着的增益[Nature Photonics 11,441(2017)]。
英文摘要:
Optical neural network (ONN) is emerging as an attractive proposal for machine-learning applications, enabling high-speed computation with low-energy consumption. However, there are several challenges in applying ONN for industrial applications, including the realization of activation functions and maintaining stability. In particular, the stability of ONNs decrease with the circuit depth, limiting the scalability of the ONNs for practical uses. Here we demonstrate how to compress the circuit depth of ONN to scale only logarithmically, leading to an exponential gain in terms of noise robustness. Our low-depth (LD) ONN is based on an architecture, called Optical CompuTing Of dot-Product UnitS (OCTOPUS), which can also be applied individually as a linear perceptron for solving classification problems. Using the standard data set of Letter Recognition, we present numerical evidence showing that LD-ONN can exhibit a significant gain in noise robustness, compared with a previous ONN proposal based on singular-value decomposition [Nature Photonics 11, 441 (2017)].
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。