Embedded Artificial Intelligence (EAI) integrates AI technologies with resource-constrained embedded systems, overcoming the limitations of cloud AI in aspects such as latency and energy consumption, thereby empowering edge devices with autonomous decision-making and real-time intelligence. This review provides a comprehensive overview of this rapidly evolving field, systematically covering its definition, hardware platforms, software frameworks and tools, core algorithms (including lightweight models), and detailed deployment processes. It also discusses its widespread applications in key areas like autonomous driving and smart Internet of Things (IoT), as well as emerging directions. By analyzing its core challenges and innovative opportunities in algorithms, hardware, and frameworks, this review aims to provide relevant researchers and developers with a practical guidance framework, promoting technological innovation and adoption.

This concise review summarizes recent advancements in theoretical studies of vortex quantum droplets (VQDs) in matter-wave fields. These are robust self-trapped vortical states in two- and three-dimensional (2D and 3D) Bose–Einstein condensates (BECs) with intrinsic nonlinearity. Stability of VQDs is provided by additional nonlinearities resulting from quantum fluctuations around mean-field states, often referred to as the Lee–Huang–Yang (LHY) corrections. The basic models are presented, with emphasis on the interplay between the mean-field nonlinearity, LHY correction, and spatial dimension, which determines the structure and stability of VQDs. We embark by delineating fundamental properties of VQDs in the 3D free space, followed by consideration of their counterparts in the 2D setting. Additionally, we address stabilization of matter-wave VQDs by optical potentials. Finally, we summarize results for the study of VQDs in the single-component BEC of atoms carrying magnetic moments. In that case, the anisotropy of the long-range dipole-dipole interactions endows the VQDs with unique characteristics. The results produced by the theoretical studies in this area directly propose experiments for the observation of novel physical effects in the realm of quantum matter, and suggest potential applications to the design of new schemes for processing classical and quantum information.

Wafer defect pattern recognition can help engineers improve the production process of semiconductor chips. In real industrial scenarios, the recognition of mixed-type wafer defects is difficult and the production scale of semiconductor wafers is large, which requires high accuracy and speed in wafer defect pattern recognition. This study proposes a light-weight neural network model to efficiently recognize mixed-type wafer defects. The proposed model is constructed via inverted residual convolution blocks with attention mechanisms and large kernel convolution downsampling layers. The inference speed of the inverted residual convolution block is fast, and the attention mechanism can enhance feature extraction capabilities. Large kernel convolutions help the network retain more important feature information during downsampling operations. The experimental results on the real Mixed-type WM38 dataset show that the proposed model achieves a recognition accuracy of 98.69% with only 1.01 M parameters. Compared with some popular high-performance models and light-weight models, our model has advantages in both recognition accuracy and inference speed. Finally, we deploy the model as a TensorRT engine, which significantly improves the inference speed of the model, enabling it to process more than 1300 wafer maps per second.