The simultaneous advances in artificial neural networks and photonic integration technologies have spurred extensive research in optical computing and optical neural networks (ONNs). The potential to simultaneously exploit multiple physical dimensions of time, wavelength and space give ONNs the ability to achieve computing operations with high parallelism and large‐data throughput. Different photonic multiplexing techniques based on these multiple degrees of freedom have enabled ONNs with large‐scale interconnectivity and linear computing functions. Here, we review the recent advances of ONNs based on different approaches to photonic multiplexing, and present our outlook on key technologies needed to further advance these photonic multiplexing/hybrid‐multiplexing techniques of ONNs.

In this paper, we propose a novel approach to achieve spectrum prediction, parameter fitting, inverse design, and performance optimization for the plasmonic waveguide-coupled with cavities structure (PWCCS) based on artificial neural networks (ANNs). The Fano resonance and plasmon-induced transparency effect originated from the PWCCS have been selected as illustrations to verify the effectiveness of ANNs. We use the genetic algorithm to design the network architecture and select the hyperparameters for ANNs. Once ANNs are trained by using a small sampling of the data generated by the Monte Carlo method, the transmission spectra predicted by the ANNs are quite approximate to the simulated results. The physical mechanisms behind the phenomena are discussed theoretically, and the uncertain parameters in the theoretical models are fitted by utilizing the trained ANNs. More importantly, our results demonstrate that this model-driven method not only realizes the inverse design of the PWCCS with high precision but also optimizes some critical performance metrics for the transmission spectrum. Compared with previous works, we construct a novel model-driven analysis method for the PWCCS that is expected to have significant applications in the device design, performance optimization, variability analysis, defect detection, theoretical modeling, optical interconnects, and so on.

Optics InfoBase is the Optical Society's online library for flagship journals, partnered and copublished journals, and recent proceedings from OSA conferences.

Complex-valued neural networks process both amplitude and phase information, in contrast to conventional artificial neural networks, achieving additive capabilities in recognizing phase-sensitive data inherent in wave-related phenomena. The ever-increasing data capacity and network scale place substantial demands on underlying computing hardware. In parallel with the successes and extensive efforts made in electronics, optical neuromorphic hardware is promising to achieve ultra-high computing performances due to its inherent analog architecture and wide bandwidth. Here, we report a complex-valued optical convolution accelerator operating at over 2 Tera operations per second (TOPS). With appropriately designed phasors we demonstrate its performance in the recognition of synthetic aperture radar (SAR) images captured by the Sentinel-1 satellite, which are inherently complex-valued and more intricate than what optical neural networks have previously processed. Experimental tests with 500 images yield an 83.8% accuracy, close to in-silico results. This approach facilitates feature extraction of phase-sensitive information, and represents a pivotal advance in artificial intelligence towards real-time, high-dimensional data analysis of complex and dynamic environments.

Recently, optical neural networks (ONNs) integrated into photonic chips have received extensive attention because they are expected to implement the same pattern recognition tasks in electronic platforms with high efficiency and low power consumption. However, there are no efficient learning algorithms for the training of ONNs on an on-chip integration system. In this article, we propose a novel learning strategy based on neuroevolution to design and train ONNs. Two typical neuroevolution algorithms are used to determine the hyper-parameters of ONNs and to optimize the weights (phase shifters) in the connections. To demonstrate the effectiveness of the training algorithms, the trained ONNs are applied in classification tasks for an iris plants dataset, a wine recognition dataset and modulation formats recognition. The calculated results demonstrate that the accuracy and stability of the training algorithms based on neuroevolution are competitive with other traditional learning algorithms. In comparison to previous works, we introduce an efficient training method for ONNs and demonstrate their broad application prospects in pattern recognition, reinforcement learning and so on.

Short-time Fourier transform (STFT) is a fundamental concept that enables the observation of dynamic spectral evolution for non-stationary signals. Broadband STFT based on digital signal processing (DSP) usually has limited acquisition frame rate, which is inherently constrained by the performance limitations of present DSP engine. The further extended acquisition frame rate can be achieved by all-optical spectrum analysis approaches, while the frequency resolution is usually worse than 1 GHz. In this paper, STFT based on bandwidth-scaled microwave photonics is proposed, where the requirement for dispersion is relaxed and the attendant transmission delay in dispersive media is greatly reduced. Moreover, the frequency resolution towards MHz level could be expected in the proposed STFT. We prove that “bandwidth scaling” combined with periodic wavelength-to-time mapping (WTM) mathematically agrees with the definition of STFT. The method of customizing system parameters according to the requirements of ultrafast spectrum measurement is carefully clarified. Experimentally, joint time-frequency analysis for a variety of ultrafast non-stationary RF signals is demonstrated, where dynamic frequency resolution of 60 MHz, dynamic observation bandwidth of 1.98 GHz and acquisition frame rate of 160 MHz are simultaneously realized. The scheme we proposed is promising for the dynamic spectrum monitoring of broadband non-stationary RF signals.