Particle swarm optimization (PSO) is a well-known optimization algorithm that shows good performances in solving different optimization problems. However, the PSO usually suffers from slow convergence. In this article, a reinforcement-learning-based parameter adaptation method (RLAM) is developed to enhance the PSO convergence by designing a network to control the coefficients of the PSO. Moreover, based on the RLAM, a new reinforcement-learning-based PSO (RLPSO) algorithm is designed. To investigate the performance of the RLAM and RLPSO, experiments on 28 CEC 2013 benchmark functions were carried out to compare with other adaptation methods and PSO variants. The reported computational results showed that the proposed RLAM is efficient and effective and that the proposed RLPSO is superior to several state-of-the-art PSO variants.

Just like its remarkable achievements in many computer vision tasks, the convolutional neural networks provide an end‐to‐end solution in handwritten Chinese character recognition (HCCR) with great success. However, the process of learning discriminative features for image recognition is difficult in cases where little data is available. In this study, the authors propose a novel method for learning siamese neural network which employs a special structure to predict the similarity between handwritten Chinese characters and template images. The optimisation of siamese neural network can be treated as a simple binary classification problem. When the training process finished, the powerful discriminative features will help to generalise the predictive power not just to new data, but to entirely new classes that never appear in the training set. Experiments performed on the ICDAR‐2013 offline HCCR datasets have shown that the proposed method has a very promising generalisation ability for new classes that never appear in the training set.

The limited computing resources on edge devices such as Unmanned Aerial Vehicles (UAVs) mean that lightweight object detection algorithms based on convolution neural networks require significant development. However, lightweight models are challenged by small targets with few available features. In this paper, we propose an LC-YOLO model that uses detailed information about small targets in each layer to improve detection performance. The model is improved from the one-stage detector, and contains two optimization modules: Laplace Bottleneck (LB) and Cross-Layer Attention Upsampling (CLAU). The LB module is proposed to enhance shallow features by integrating prior information into the convolutional neural network and maximizing knowledge sharing within the network. CLAU is designed for the pixel-level fusion of deep features and shallow features. Under the combined action of these two modules, the LC-YOLO model achieves better detection performance on the small object detection task. The LC-YOLO model with a parameter quantity of 7.30M achieves an mAP of 94.96% on the remote sensing dataset UCAS-AOD, surpassing the YOLOv5l model with a parameter quantity of 46.61M. The tiny version of LC-YOLO with 1.83M parameters achieves 94.17% mAP, which is close to YOLOv5l. Therefore, the LC-YOLO model can replace many heavyweight networks to complete the small target high-precision detection task under limited computing resources, as in the case of mobile edge-end chips such as UAV onboard chips.

In password guessing, the Markov model is still widely used due to its simple structure and fast inference speed. However, the Markov model based on random sampling to generate passwords has the problem of a high repetition rate, which leads to a low cover rate. The model based on enumeration has a lower cover rate for high-probability passwords, and it is a deterministic algorithm that always generates the same passwords in the same order, making it vulnerable to attack. We design a dynamic distribution mechanism based on the random sampling method. This mechanism enables the probability distribution of passwords to be dynamically adjusted and tend toward uniform distribution strictly during the generation process. We apply the dynamic distribution mechanism to the Markov model and propose a dynamic Markov model. Through comparative experiments on the RockYou dataset, we set the optimal adjustment degree $\alpha$. Compared with the Markov model without the dynamic distribution mechanism, the dynamic Markov model reduced the repetition rate from 75.88% to 66.50% and increased the cover rate from 37.65% to 43.49%. In addition, the dynamic Markov model had the highest cover rate for high-probability passwords. Finally, the model avoided the lack of a deterministic algorithm, and when it was run five times, it reached almost the same cover rate as OMEN.

Blockwise reconstruction with adaptive rounding helps achieve acceptable 4-bit post-training quantization accuracy. However, adaptive rounding is time intensive, and the optimization space of weight elements is constrained to a binary set, thus limiting the performance of quantized models. The optimality of block-wise reconstruction requires that subsequent network blocks remain unquantized. To address this, we propose a two-stage post-training quantization scheme, AE-Qdrop, encompassing block-wise reconstruction and global fine-tuning. In the block-wise reconstruction stage, a progressive optimization strategy is introduced as a replacement for adaptive rounding, enhancing both quantization accuracy and efficiency. Additionally, the integration of randomly weighted quantized activation helps mitigate the risk of overfitting. In the global fine-tuning stage, the weights of each quantized network block are corrected simultaneously through logit matching and feature matching. Experiments in image classification and object detection tasks validate that AE-Qdrop achieves high precision and efficient quantization. For the 2-bit MobileNetV2, AE-Qdrop outperforms Qdrop in quantization accuracy by 6.26%, and its quantization efficiency is fivefold higher.