Hermans Michiel, Antonik Piotr, Haelterman Marc, Massar Serge
Laboratoire d'Information Quantique, Université libre de Bruxelles, 50 Avenue F. D. Roosevelt, CP 224, B-1050 Brussels, Belgium.
Service OPERA-Photonique, Université libre de Bruxelles, 50 Avenue F. D. Roosevelt, CP 194/5, B-1050 Brussels, Belgium.
Phys Rev Lett. 2016 Sep 16;117(12):128301. doi: 10.1103/PhysRevLett.117.128301.
Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular, it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here, we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared to when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.
延迟耦合电光系统因其动力学特性及其在信号处理中的潜在应用而备受关注。特别是，最近已经证明，使用称为储层计算的人工智能算法，这种系统的光子实现能够解决诸如语音识别等复杂任务。在这里，我们展示了反向传播算法如何能够在用于计算的相同电光延迟耦合架构上进行物理实现，只需对原始设计进行微小更改。我们发现，与不使用反向传播算法时相比，在三个基准任务上评估的所得计算设备的错误率大幅降低。这表明电光模拟计算机可以体现其自身训练过程的很大一部分，使其能够应用于新的、更困难的任务。
