Detecting orbital angular momentum (OAM) modes with high-speed and -accuracy is always a challenge in the practical applications of vortex beams (VBs). Here, we design a multilayer feed-forward neural network (FNN) model to rapidly identify OAM modes. After trained with loads of learning samples influenced by the transmission distance, beam waist, and atmospheric turbulence, the model shows a good generalization ability in quickly identifying the OAM mode of VBs ranging from -25 to +25. The classification accuracy reaches 99.55% under the influence of moderate turbulence and achieves 68.53% even under strong turbulence. Furthermore, we construct a communication link to deliver a 100×100 pixels Lena gray image by encoding OAM modes. After free-space transmission, the OAM-SK signals are demodulated by the FNN model, and the Lena gray image is well reconstituted. With an i5-6500 CPU, the identification process takes only $7.5 \times 10^{-5}$ s per OAM mode. These numerical simulation results demonstrate that the proposed FNN model provides a feasible way to rapidly identify the OAM modes of VBs and may show great potential in the optical OAM communication, etc.
Optical bistability plays a vital role in high-performance all-optical devices. In this work, we construct a heterostructure consisting of distributed Bragg reflectors (DBRs) and three-dimensional Dirac semimetal (3D DSM), where a 3D DSM layer is sandwiched between two DBRs with mismatched central resonant wavelengths to realize effective excitation and coupling of optical Tamm states (OTSs). Benefiting from the strong optical field confinement and intrinsic Kerr nonlinearity of 3D DSM, the proposed structure achieves a low bistability threshold of 105 V/m. Moreover, the bistability performance can be tuned by modifying the Fermi level of 3D DSM and adjusting the incident angle. The proposed structure offers a promising theoretical platform for the future development of low-power terahertz bistable devices.