Optical neural networks (ONNs), or optical neuromorphic hardware accelerators, have the
potential to dramatically enhance the computing power and energy efficiency of mainstream …

The independent tailoring of wave quantities lays the foundation for controlling wave
phenomena and designing wave devices. The concept of isospectrality, which suggests the …

Compared with electrons, photons have the potential to realise ultra‐high speed operations
because of its unique high speed and high parallelism. In recent years, there have been …

Developing hardware for high-dimensional unitary operators plays a vital role in
implementing quantum computations and deep learning accelerations. Programmable …

摘要光学神经网络是区别于冯· 诺依曼计算架构的一种高性能新型计算范式, 具有低延时,
低功耗, 大带宽以及并行信号处理等优势. 片上集成是光学神经网络微型化发展的一种典型方式 …

Integrated photonic neural networks (IPNNs) are emerging as promising successors to
conventional electronic AI accelerators as they offer substantial improvements in computing …

Non-Hermitian photonic systems with loss and gain attract much attention due to their
exceptional abilities in molding the flow of light. Introducing asymmetry to the PT-symmetric …

Recently, the diffractive deep neural network (D^ 2NN) has demonstrated the advantages to
achieve large-scale computational tasks in terms of high speed, low power consumption …

Metallic nanostructures endowed with optical gain are promising building blocks for the
development of active nanophotonic devices with enhanced optical responses as well as for …

Artificial neural networks are efficient computing platforms inspired by the brain. Such
platforms can tackle a vast area of real-life tasks ranging from image processing to language …