| Autor: |
Tait AN; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA. atait@princeton.edu., de Lima TF; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA., Zhou E; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA., Wu AX; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA., Nahmias MA; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA., Shastri BJ; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA., Prucnal PR; Department of Electrical Engineering, Princeton University, Princeton, New Jersey, 08544, USA. |
| Abstrakt: |
Photonic systems for high-performance information processing have attracted renewed interest. Neuromorphic silicon photonics has the potential to integrate processing functions that vastly exceed the capabilities of electronics. We report first observations of a recurrent silicon photonic neural network, in which connections are configured by microring weight banks. A mathematical isomorphism between the silicon photonic circuit and a continuous neural network model is demonstrated through dynamical bifurcation analysis. Exploiting this isomorphism, a simulated 24-node silicon photonic neural network is programmed using "neural compiler" to solve a differential system emulation task. A 294-fold acceleration against a conventional benchmark is predicted. We also propose and derive power consumption analysis for modulator-class neurons that, as opposed to laser-class neurons, are compatible with silicon photonic platforms. At increased scale, Neuromorphic silicon photonics could access new regimes of ultrafast information processing for radio, control, and scientific computing. |
