SUANPAN: Scalable Photonic Linear Vector Machine

Photonics is promising to handle extensive vector multiplications in artificial intelligence (AI) techniques due to natural bosonic parallelism and high-speed information transmission. However, the dimensionality of current photonic linear operation is limited and tough to improve due to the complex beam-interaction for implementing optical matrix operation and digital-analog conversions. Here, we propose a programmable and reconfigurable photonic linear vector machine with extreme scalability formed by a series of emitter-detector pairs as the independent basic computing units. The elemental values of two high-dimensional vectors are prepared on emitter-detector pairs by bit encoding and analog detecting method without requiring large-scale analog-to-digital converter or digital-to-analog converter arrays. Since there is no interaction among light beams inside, extreme scalability could be achieved by simply multiplicating the independent emitter-detector pair. The proposed architecture is inspired by the traditional Chinese Suanpan or abacus, and thus is denoted as photonic SUANPAN. Experimentally, the computing fidelities for vector inner products could achieve > 98% in our implemented SUANPAN with an 8×8 vertical cavity surface emission laser (VCSEL) array and an 8×8 MoTe ₂ two-dimensional material photodetector array. Furthermore, SUANPAN is applied on two typical AI tasks as 1024-dimensional optimization problem is successfully solved and competitive classification accuracy of 88% is achieved for handwritten digit dataset. We believe that the photonic SUANPAN could serve as a fundamental linear vector machine and enhance various future AI applications.