Lossless Monolithically Integrated Photonic InP Neuron for All-Optical Computation

We demonstrate a monolithically integrated SOA-based photonic neuron, including both the weighted addition and a wavelength converter with tunable laser as nonlinear function, allowing for lossless computation of 8 Giga operation/s with an 89% accuracy.

[1]  N. Calabretta,et al.  SOA-Based Photonic Integrated Deep Neural Networks for Image Classification , 2019, 2019 Conference on Lasers and Electro-Optics (CLEO).

[2]  Thomas N. Theis,et al.  The End of Moore's Law: A New Beginning for Information Technology , 2017, Computing in Science & Engineering.

[3]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

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

[5]  K Vyrsokinos,et al.  An all-optical neuron with sigmoid activation function. , 2019, Optics express.

[6]  Paul R. Prucnal,et al.  Principles of Neuromorphic Photonics , 2017, ArXiv.

[7]  Nicola Calabretta,et al.  First demonstration of a two-layer all-optical neural network by using photonic integrated chips and SOAs , 2019 .

[8]  D. Lenstra,et al.  Widely tunable Coupled Cavity Laser based on a Michelson interferometer with doubled free spectral range , 2015, 2015 Optical Fiber Communications Conference and Exhibition (OFC).