With an ongoing trend in computing hardware toward increased heterogeneity, domain-specific coprocessors are emerging as alternatives to centralized paradigms. The tensor core unit has been shown to outperform graphic processing units by almost 3 orders of magnitude, enabled by a stronger signal and greater energy efficiency. In this context, photons bear several synergistic physical properties while phase-change materials allow for local nonvolatile mnemonic functionality in these emerging distributed non-von Neumann architectures. While several photonic neural network designs have been explored, a photonic tensor core to perform tensor operations is yet to be implemented. In this manuscript, we introduce an integrated photonics-based tensor core unit by strategically utilizing (i) photonic parallelism via wavelength division multiplexing, (ii) high 2 peta-operations-per-second throughputs enabled by tens of picosecond-short delays from optoelectronics and compact photonic integrated circuitry, and (iii) near-zero static power-consuming novel photonic multi-state memories based on phase-change materials featuring vanishing losses in the amorphous state. Combining these physical synergies of material, function, and system, we show, supported by numerical simulations, that the performance of this 4-bit photonic tensor core unit can be 1 order of magnitude higher for electrical data. The full potential of this photonic tensor processor is delivered for optical data being processed, where we find a 2–3 orders higher performance (operations per joule), as compared to an electrical tensor core unit, while featuring similar chip areas. This work shows that photonic specialized processors have the potential to augment electronic systems and may perform exceptionally well in network-edge devices in the looming 5G networks and beyond.

Recently, integrated optics has become a functional platform for implementing machine learning algorithms and, in particular, neural networks. Photonic integrated circuits can straightforwardly perform vector-matrix multiplications with high efficiency and low power consumption by using weighting mechanism through linear optics. However, this cannot be said for the activation function, i.e., “threshold,” which requires either nonlinear optics or an electro-optic module with an appropriate dynamic range. Even though all-optical nonlinear optics is potentially faster, its current integration is challenging and is rather inefficient. Here, we demonstrate an electroabsorption modulator based on an indium tin oxide layer monolithically integrated into silicon photonic waveguides, whose dynamic range is used as a nonlinear activation function of a photonic neuron. The thresholding mechanism is based on a photodiode, which integrates the weighed products, and whose photovoltage drives the electroabsorption modulator. The synapse and neuron circuit is then constructed to execute a 200-node MNIST classification neural network used for benchmarking the nonlinear activation function and compared with an equivalent electronic module.

The state-of-the-art hardware in artificial neural networks is still affected by the same capacitive challenges known from electronic integrated circuits. Unlike other emerging electronic technologies, photonics provides low-delay interconnectivity suitable for node-distributed non-von Neumann architectures, relying on dense node-to-node communication. Here, we provide a roadmap to pave the way for emerging hybridized photonic-electronic neural networks by taking a detailed look into a single node perceptron. We discuss how it can be realized in hybrid photonic-electronic heterogeneous technologies. Furthermore, we assess that electro-optic devices based on phase change or strong carrier dispersive effects could provide a viable path for both the perceptron “weights” and the nonlinear activation function in trained neural networks, while simultaneously being foundry process-near materials. This study also assesses the advantages of using nonlinear optical materials as efficient and instantaneous activation functions. We finally identify several challenges that, if solved, could accelerate the adoption of such heterogeneous integration strategies of emerging memory materials into integrated photonics platforms for near real-time responsive neural networks.

The replacement of plastic with eco-friendly and biodegradable materials is one of the most stringent environmental challenges. In this respect, cellulose outstands as a biodegradable polymer. However, a significant challenge is to obtain biodegradable materials for high-end photonics that are robust in humid environments. Here, we demonstrate the fabrication of high quality micro- and nanoscale photonic and plasmonic structures via replica molding using pure cellulose and a blended version with non-edible agro-wastes. Both materials are biodegradable in soil and seawater according to the ISO 17556 standard. The pure cellulose films are transparent in the VIS-NIR spectrum having a refractive index similar to glass. The microstructured photonic crystals show high-quality diffractive properties that are maintained under extended exposure to water. Nanostructuring the cellulose transforms it to a biodegradable metasurface manifesting bright structural colours. A subsequent deposition of Ag endowed the metasurface with plasmonic properties used to produce plasmonic colours and for surface-enhanced Raman scattering (SERS).