Reservoir computing is a relatively recent computational paradigm that originates from a recurrent neural network, and is known for its wide-range of implementations using different physical technologies. Large reservoirs are very hard to obtain in conventional computers as both the computation complexity and memory usage grows quadratically. We propose an optical scheme performing reservoir computing over very large networks of up to $10^6$ fully connected photonic nodes thanks to its intrinsic properties of parallelism. Our experimental studies confirm that in contrast to conventional computers, the computation time of our optical scheme is only linearly dependent on the number of photonic nodes of the network, which is due to electronic overheads, while the optical part of computation remains fully parallel and independent of the reservoir size. To demonstrate the scalability of our optical scheme, we perform for the first time predictions on large multidimensional chaotic datasets using the Kuramoto-Sivashinsky equation as an example of a spatiotemporal chaotic system. Our results are extremely challenging for conventional Turing-von Neumann machines, and they significantly advance the state-of-the-art of unconventional reservoir computing approaches in general.

中文翻译：

---

用于时空混沌系统预测的大规模光库计算

水库计算是一种相对较新的计算范式，它起源于循环神经网络，并以其使用不同物理技术的广泛实现而闻名。由于计算复杂度和内存使用量均呈二次增长，因此在传统计算机中很难获得大型水库。由于其并行性的内在特性，我们提出了一种在高达 10^6 美元的全连接光子节点的非常大的网络上执行储层计算的光学方案。我们的实验研究证实，与传统计算机相比，我们的光学方案的计算时间仅线性依赖于网络的光子节点数量，这是由于电子开销，而计算的光学部分保持完全平行且独立于储层大小。为了证明我们的光学方案的可扩展性，我们首次使用 Kuramoto-Sivashinsky 方程作为时空混沌系统的示例对大型多维混沌数据集进行了预测。我们的结果对于传统的 Turing-von Neumann 机器极具挑战性，并且它们总体上显着推进了非常规储层计算方法的最新技术水平。