论文标题
大规模光子自然语言处理
Large-scale photonic natural language processing
论文作者
论文摘要
现代的机器学习应用需要庞大的人工网络，要求计算能力和内存。基于光的平台有望超快速和节能硬件，这可能有助于实现下一代数据处理设备。但是，当前的光子网络受到可以单次拍摄的输入输出节点的数量的限制。这种限制的网络容量阻止了他们在相关的大规模问题（例如自然语言处理）中的应用。在这里，我们实现了一个超过$ 1.5 \ times 10^{10} $光学节点的光子处理器，比任何一个以前的实现都要大一个数量级，该级数超过一个数量级，该实现可以实现光子大规模的文本编码和分类。通过利用光场在自由空间中传播的完整三维结构，我们克服了插值阈值并达到机器学习的过度参数化区域，这种情况可以允许高性能自然语言处理，而训练点最少。我们的结果为扩大光驱动计算并打开光子语言处理的途径提供了一种新颖的解决方案。
Modern machine learning applications require huge artificial networks demanding in computational power and memory. Light-based platforms promise ultra-fast and energy-efficient hardware, which may help in realizing next-generation data processing devices. However, current photonic networks are limited by the number of input-output nodes that can be processed in a single shot. This restricted network capacity prevents their application to relevant large-scale problems such as natural language processing. Here, we realize a photonic processor with a capacity exceeding $1.5 \times 10^{10}$ optical nodes, more than one order of magnitude larger than any previous implementation, which enables photonic large-scale text encoding and classification. By exploiting the full three-dimensional structure of the optical field propagating in free space, we overcome the interpolation threshold and reach the over-parametrized region of machine learning, a condition that allows high-performance natural language processing with a minimal fraction of training points. Our results provide a novel solution to scale-up light-driven computing and open the route to photonic language processing.
