S22-140 Efficient Analog Backpropagation Training Architecture for Photonic Neural Networks Stanford researchers design and demonstrate a novel in situ backpropagation training algorithm for photonic implementations of neural networks. Sunil Pai David Miller Olav Solgaard Shanhui Fan Tyler Hughes Ian Williamson Momchil Minkov Zhanghao Sun
S22-139 LightHash: Photonic Blockchain Based on Optical Proof-of-Work Stanford inventors have developed a framework that performs digitally verifiable photonic matrix-vector multiplication in integrated photonic networks, which may potentially enable energy-efficient hash functions and cryptocurrency mining. Sunil Pai David Miller Olav Solgaard Shanhui Fan Michael Dubrovsky Bogdan Penkovsky Marshall Ball