With the rapid development of artificial intelligence (AI) technology, artificial neural networks (ANNs) have achieved significant success in multiple fields. However, traditional neural network training methods—especially the backpropagation algorithm—face numerous challenges in hardware implementation. Although the backpropagation algorithm is ef...

Academic Background With the advent of the information age, integrated circuits (ICs) have become the driving force behind technological advancements. However, traditional integrated photonics platforms, such as silicon and silicon nitride, face numerous limitations in material properties. For instance, silicon’s indirect bandgap restricts its use ...

Carbon nitride (CN), as a two-dimensional n-type semiconductor material, exhibits great potential in light-driven energy conversion and environmental applications due to its excellent photocatalytic activity and stability. However, despite its outstanding performance in photocatalysis, the application of CN in optoelectronic devices, especially sil...

Theory and Application of Complex Quantized Minimum Error Entropy with Fiducial Points: Breakthroughs in Model Regression Academic Background In the fields of machine learning and signal processing, the presence of non-Gaussian noise often adversely affects model performance. Although the traditional Mean Squared Error (MSE) is theoretically and co...

Research on Abnormal Behavior Detection in Surveillance Video Based on Probabilistic Memory Auto-Encoding Network Academic Background In intelligent surveillance systems, abnormal behavior detection is a crucial function widely applied in anti-terrorism, social stability maintenance, and public safety assurance. However, a core challenge in abnorma...