Implementing any linear transformation matrix through the optical channels of an on-chip reconfigurable multiport interferometer has been emerging as a promising technique for various fields of study, such as information processing and optical communication systems. Recently, the use of multiport optical interferometric-based linear structures in neural networks has attracted a great deal of attention. Optical neural networks have proven to be promising in terms of computational speed and power efficiency, allowing for the increasingly large neural networks that are being created today. This paper demonstrates the experimental analysis of programming a 4×4 reconfigurable optical processor using a unitary transformation matrix implemented by a single layer neural network. To this end, the Mach-Zehnder interferometers (MZIs) in the structure are first experimentally calibrated to circumvent the random phase errors originating from fabrication process variations. The linear transformation matrix of the given application can be implemented by the successive multiplications of the unitary transformation matrices of the constituent MZIs in the optical structure. The required phase shifts to construct the linear transformation matrix by means of the optical processor are determined theoretically. Using this method, a single layer neural network is trained to classify a synthetic linearly separable multivariate Gaussian dataset on a conventional computer using a stochastic optimization algorithm. Additionally, the effect of the phase errors and experimental equipment inaccuracies and the device components imperfections is also analyzed and simulated. Finally, the optical processor is experimentally programmed by applying the obtained phase shifts from the matrix decomposition process to the corresponding phase shifters in the device. The experimental results show that the optical processor achieves 72% classification accuracy compared to the 98.9% of the simulated optical neural network on a digital computer.

Developing compute platforms capable of performing computations at high speed is essential for data processing in the next generation of data centers and edge devices. A neuromorphic photonic accelerator on a silicon photonic platform is a promising solution. Compared to silicon photonic data communication transceiver modules, neuromorphic photonic accelerators constitute a large number of active and passive components and optoelectronic devices to handle the parallel processing. Thus, an increased number of optical and electrical interconnects are required, making the packaging of such processors challenging. Moreover, thermal and electrical crosstalk can dramatically degrade the performance of such processors. Thus, packaging a neuromorphic photonic accelerator for efficient processing and data movement requires careful considerations at the chip, module, and board levels. This work investigates the challenges and potential solutions for optical coupling, optical and electrical interconnections, processor-memory communication, and thermal and electrical cross-talk to develop neuromorphic photonic accelerators.

We investigate the influence of localized and propagating surface plasmons on third harmonic generation from rectangular apertures in metal films. We designed optimal aperture array structures by using finite-difference time-domain simulations with nonlinear scattering theory. From this design space, we fabricated and measured the third harmonic in the region of maximal performance. We find the highest third harmonic conversion efficiency when the localized resonance is tuned to the fundamental wavelength and the propagating (Bragg) resonance is tuned to the third harmonic; this is 2.5 times larger than the case where the both localized and propagating are tuned to the fundamental wavelength. The two remaining configurations where also investigated with much lower conversion efficiency. When the Bragg resonance is tuned to the third harmonic, directivity improves the collection of third harmonic emission. On the other hand, due to the inherent absorption of gold at the third harmonic, tuning the localized surface plasmon resonance to the third harmonic is less beneficial. All cases showed quantitative agreement with the original theoretical analysis. This work points towards an optimal design criterion for harmonic generation from thin plasmonic metasurfaces.