论文信息 - Parallel Fault-Tolerant Programming and Optimization of Photonic Neural Networks

Parallel Fault-Tolerant Programming and Optimization of Photonic Neural Networks

We propose and numerically demonstrate a fault-tolerant, efficient parallel nullification protocol to program and error-correct photonic neural networks for energy-efficient machine learning tasks.

[1] David A. B. Miller,et al. Setting up meshes of interferometers - reversed local light interference method , 2017 .

[2] Dirk Englund,et al. Deep learning with coherent nanophotonic circuits , 2017, 2017 Fifth Berkeley Symposium on Energy Efficient Electronic Systems & Steep Transistors Workshop (E3S).

[3] David A. B. Miller,et al. Matrix optimization on universal unitary photonic devices , 2018, Physical Review Applied.

[4] Shanhui Fan,et al. Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks , 2019, IEEE Journal of Selected Topics in Quantum Electronics.

[5] David A. B. Miller,et al. Parallel fault-tolerant programming of an arbitrary feedforward photonic network , 2019, ArXiv.

[6] Gregory R. Steinbrecher,et al. High-fidelity quantum state evolution in imperfect photonic integrated circuits , 2015 .