Scalable Non-Volatile Tuning of Photonic Computational Memories by Automated Silicon Ion Implantation.

Photonic integrated circuits (PICs) are revolutionizing the realm of information technology, promising unprecedented speeds and efficiency in data processing and optical communication. However, the nanoscale precision required to fabricate these circuits at scale presents significant challenges, due to the need to maintain consistency across wavelength-selective components, which necessitates individualized adjustments after fabrication. Harnessing spectral alignment by automated silicon ion implantation, in this work scalable and non-volatile photonic computational memories are demonstrated in high-quality resonant devices. Precise spectral trimming of large-scale photonic ensembles from a few picometers to several nanometres is achieved with long-term stability and marginal loss penalty. Based on this approach, spectrally aligned photonic memory and computing systems for general matrix multiplication are demonstrated, enabling wavelength multiplexed integrated architectures at large scales.

Event-driven adaptive optical neural network.

We present an adaptive optical neural network based on a large-scale event-driven architecture. In addition to changing the synaptic weights (synaptic plasticity), the optical neural network's structure can also be reconfigured enabling various functionalities (structural plasticity). Key building blocks are wavelength-addressable artificial neurons with embedded phase-change materials that implement nonlinear activation functions and nonvolatile memory. Using multimode focusing, the activation function features both excitatory and inhibitory responses and shows a reversible switching contrast of 3.2 decibels. We train the neural network to distinguish between English and German text samples via an evolutionary algorithm. We investigate both the synaptic and structural plasticity during the training process. On the basis of this concept, we realize a large-scale network consisting of 736 subnetworks with 16 phase-change material neurons each. Overall, 8398 neurons are functional, highlighting the scalability of the photonic architecture.