A deep-learning artificial neural network (NN) combined with the particle swarm optimization (PSO) method has been proposed to inversely design the semiconductor laser with high accuracy and computational speed. This method is exempt from the single-solution problem of tandem NN and can be highly useful to extract the possible problematic parameters in the failure analysis of a device. The light-current curves and small signal responses have been tested against the benchmarks calculated by the traveling-wave model to demonstrate the NN’s robustness and efficiency in simulating the laser behavior for further use in the inverse design by PSO.

The asynchronous double deep Q-learning (A-DDQN) method is proposed to design the multi-mode interference (MMI) power splitters for low insertion loss and wide bandwidth from 1200 to 1650 nm wavelength range. By using A-DDQN to guide hole etchings in the interference region of MMI, the target splitting ratio (SR) can be obtained with much less CPU time (about 10 hours for one design) and more effective utilization of the computational resources in asynchronous/parallel manner. Also, this method can simplify the design by using relatively few holes to obtain the same SR with small return loss.

The inverse design method based on a generative adversarial network (GAN) combined with a simulation neural network (sim-NN) and the self-attention mechanism is proposed in order to improve the efficiency of GAN for designing nanophotonic devices. The sim-NN can guide the model to produce more accurate device designs via the spectrum comparison, whereas the self-attention mechanism can help to extract detailed features of the spectrum by exploring their global interconnections. The nanopatterned power splitter with a 2 μm × 2 μm interference region is designed as an example to obtain the average high transmission (>94%) and low back-reflection (<0.5%) over the broad wavelength range of 1200~1650 nm. As compared to other models, this method can produce larger proportions of high figure-of-merit devices with various desired power-splitting ratios.

The NN (neural network)-PSO (particle swarm optimization) method is demonstrated to be able to inversely extract the coating parameters for the multilayer nano-films through a simulation case and two experimental cases to verify its accuracy and robustness. In the simulation case, the relative error (RE) between the average layer values and the original one was less than 3.45% for 50 inverse designs. In the experimental anti-reflection (AR) coating case, the mean thickness values of the inverse design results had a RE of around 5.05%, and in the Bragg reflector case, the RE was less than 1.03% for the repeated inverse simulations. The method can also be used to solve the single-solution problem of a tandem neural network in the inverse process.

A parity-time symmetric vertical Bragg reflection waveguide structure is proposed and analyzed for realizing single-mode operation of a laser diode. Impact of the key design parameters on laser performance are investigated for the purpose of achieving high side-mode suppression ratio and high injection slope efficiency. Our studies indicate that an electrically pumped edge-emitting single-mode laser is possible with proper design. Such lasers exhibit a number of highly desirable and in some cases unique characteristics, such as high-modulation bandwidth, high transverse gain, and high confinement of optical field in the low-effective index Fabry-Perot cavity.