Search

Photonic neural networks benefit from both the high-channel capacity and the wave nature of light acting as an effective weighting mechanism through linear optics. Incorporating a nonlinear activation function by using active integrated photonic components allows neural networks with multiple layers to be built monolithically, eliminating the need for energy and latency costs due to external conversion. Interferometer-based modulators, while popular in communications, have been shown to require more area than absorption-based modulators, resulting in a reduced neural network density. Here, we develop a model for absorption modulators in an electro-optic fully connected neural network, including noise, and compare the network's performance with the activation functions produced intrinsically by five types of absorption modulators. Our results show the quantum well absorption modulator-based electro-optic neuron has the best performance allowing for 96% prediction accuracy with 1.7×10 -12 J/MAC excluding laser power when performing MNIST classification in a 2 hidden layer feed-forward photonic neural network.

While augmenting network on chips (NoC) with photonic links enables high-bandwidth communication, the overhead for photonics is rather large, mainly driven by bulky footprints and the multi-functionality of transceivers. The latter requires, in addition to a photon source, signal modulation and detection. If the NoC were photonically augmented at every network point to enable all-to-all connectivity, the resulting photonic overhead would be excessive. Besides, the high bandwidth of a single optical bus may be sufficient to supply the data-sharing demand of a network. Spatial signal routing is a necessary function of data communication in NoCs. However, if photonic links are used to augment electronics, an energy-costly optical-electrical-optical (OEO) conversion is required since routing is currently executed in the electronic domain. Here we show a novel integrated broadband hybrid photonic-plasmonic device termed an MO detector featuring dual light modulation and detection. With 10 dB extinction ratio and 0.8 dB insertion loss at the modulation state and 0.7 A/W responsivity at the detection state based on the finite-different time-domain simulation, this transceiver-like device (i) eliminates the OEO conversion, (ii) reduces optical losses from photodetectors via bypassing the photodetector when not needed, and (iii) enables cognitive routing strategies for network-on-chips. As such, the MO detector acts as a micrometer-compact transceiver for next-generation NoCs.