Presented is a novel way to combine snapshot compressive imaging and lateral shearing interferometry in order to capture the spatio-spectral phase of an ultrashort laser pulse in a single shot. A deep unrolling algorithm is utilized for snapshot compressive imaging reconstruction due to its parameter efficiency and superior speed relative to other methods, potentially allowing for online reconstruction. The algorithm’s regularization term is represented using a neural network with 3D convolutional layers to exploit the spatio-spectral correlations that exist in laser wavefronts. Compressed sensing is not typically applied to modulated signals, but we demonstrate its success here. Furthermore, we train a neural network to predict the wavefronts from a lateral shearing interferogram in terms of Zernike polynomials, which again increases the speed of our technique without sacrificing fidelity. This method is supported with simulation-based results. While applied to the example of lateral shearing interferometry, the methods presented here are generally applicable to a wide range of signals, including Shack–Hartmann-type sensors. The results may be of interest beyond the context of laser wavefront characterization, including within quantitative phase imaging.

The creation of biomimetic neuron interfaces (BNIs) has become imperative for different research fields from neural science to artificial intelligence. BNIs are two-dimensional or three-dimensional (3D) artificial interfaces mimicking the geometrical and functional characteristics of biological neural networks to rebuild, understand, and improve neuronal functions. The study of BNI holds the key for curing neuron disorder diseases and creating innovative artificial neural networks (ANNs). To achieve these goals, 3D direct laser writing (DLW) has proven to be a powerful method for BNI with complex geometries. However, the need for scaled-up, high speed fabrication of BNI demands the integration of DLW techniques with ANNs. ANNs, computing algorithms inspired by biological neurons, have shown their unprecedented ability to improve efficiency in data processing. The integration of ANNs and DLW techniques promises an innovative pathway for efficient fabrication of large-scale BNI and can also inspire the design and optimization of novel BNI for ANNs. This perspective reviews advances in DLW of BNI and discusses the role of ANNs in the design and fabrication of BNI.

近年来自适应光学（AO）系统向着小型化和低成本化趋势发展，无波前探测自适应光学（WFSless AO）系统由于结构简单、应用范围广，成为目前相关领域的研究热点。硬件环境确定后，系统控制算法决定了WFSless AO系统的校正效果和系统收敛速度。新兴的深度学习及人工神经网络为WFSless AO系统控制算法注入了新的活力，进一步推动了WFSless AO系统的理论发展与应用发展。在回顾前期WFSless AO系统控制算法的基础上，全面介绍了近年来卷积神经网络（CNN）、长短期记忆神经网络（LSTM）、深度强化学习在WFSless AO系统控制中的应用，并对WFSless AO系统中各种深度学习模型的特点进行了总结。概述了WFSless AO技术在天文观测、显微成像、眼底成像、激光通信等领域的应用。

The analog photonics link (APL) is widely used in microwave photonics. However, in wideband and multi-carrier systems, the third inter-modulation distortion (IMD3) and cross-modulation distortion (XMD) will jointly limit the spurious-free dynamic range (SFDR) of links. In this paper, we experimentally present a linearized wideband and multi-carrier APL, in which the IMD3 and XMD are mitigated simultaneously by using artificial neural networks with transfer learning (TL-ANN). In this experiment, with different artificial neural networks, which are trained with the knowledge obtained from the two- or three-sub-carrier system, the IMD3 and XMD are suppressed by 21.71 dB and 11.11 dB or 22.38 dB and 16.73 dB, and the SFDR is improved by 13.4 dB or 14.3 dB, respectively. Meanwhile, compared with previous studies, this method could reduce the training time and training epochs to 16% and 25%.

In laser-pointing-related applications, when only the centroid of a laser spot is considered, then the position and angular errors of the laser beam are often coupled together. In this study, the decoupling of the position and angular errors is achieved from one single spot image by utilizing a neural network technique. In particular, the successful application of the neural network technique relies on novel experimental procedures, including using an appropriate small-focal-length lens and tilting the detector, to physically enlarge the contrast of different spots. This technique, with the corresponding new system design, may prove to be instructive in the future design of laser-pointing-related systems.