Neurocomputing最新文献

In this work, we present a novel embedded feature selection method based on a Multi-layer Perceptron (MLP) network and generalize it for group-feature or sensor selection problems, which can control the level of redundancy among the selected features or groups and it is computationally more efficient than the existing ones in the literature. Additionally, we have generalized the group lasso penalty for feature selection to encompass a mechanism for selecting valuable groups of features while simultaneously maintaining control over redundancy. We establish the monotonicity and convergence of the proposed algorithm, with a smoothed version of the penalty terms, under suitable assumptions. The effectiveness of the proposed method for both feature selection and group feature selection is validated through experimental results on various benchmark datasets. The performance of the proposed methods is compared with some state-of-the-art methods.

The rapid detection of soldering defects in printed circuit boards (PCBs) is crucial and a challenge for quality control. Thus, a novel soldering defect detection network (SDD-Net) is proposed based on improvements in YOLOv7-tiny. A fast spatial pyramid pooling block integrating a cross-stage partial network is designed to expand the receptive field and feature extraction ability of the model. A hybrid combination attention mechanism is proposed to boost feature representation. A residual feature pyramid network is subsequently presented to reinforce the capability of multilevel feature fusion to overcome the scale variance issue in PCB soldering defects. Finally, efficient intersection over union loss is applied for bounding box regression to accelerate model convergence while improving localisation precision. SDD-Net achieves a stunning mean average precision of 99.1% on the dataset, producing a 1.8% increase compared with the baseline. The detection speed is boosted to 102 frames/s for input images of 640 × 640 pixels using a mediocre processor. In addition, SDD-Net exhibits outstanding generalisation ability in two public surface defect datasets.

Graph contrastive learning has emerged as a powerful technique for dealing with graph noise and mining latent information in networks, that has been widely applied in GNN-based collaborative filtering. Traditional graph contrastive learning methods commonly generate multiple augmented views, and then learn node representations by maximizing the consistency between these views. However, on one hand, manual view construction methods necessitate expert knowledge and a trial-and-error process. On the other hand, adaptive view construction methods require decoders which results in increased training costs. To address the aforementioned limitations, in this paper, we propose the Adaptive Denoising Graph Contrastive Learning with Memory Graph Attention for Recommendation (ADGA) framework. Firstly, we introduce the memory graph attention mechanism to capture node attention during multi-hop information aggregation. Then, unlike previous methods that required additional node representations to generate views, ADGA proposes, for the first time, directly using attention to adaptively generate structure-aware contrastive learning views. It reduces the training cost of the model and improves the cross-view consistency of node representations, that offers a new paradigm for adaptive graph contrastive learning. Experimental results on three real-world datasets demonstrate that ADGA achieves state-of-the-art performance in recommendation tasks. The code is available at https://github.com/Andrewsama/ADGA.

Nonlinear spiking neural P (NSNP) systems are variants of neural-like membrane computing models, abstracted by nonlinear spiking mechanisms of biological neurons. NSNP systems can show rich nonlinear dynamics. This study proposes a new variant of NSNP systems, called $k$-order NSNP systems, and derives their mathematical models. The $k$-order NSNP systems are able to remember the states of the previous $k$ moments. Based on the $k$-order NSNP systems, we propose a new recurrent-like model, called $k$-order echo-type spiking neural P systems or termed kESNP model. Structurally, the $k$ESNP model is a $k$-order NSNP system equipped with an input layer and an output layer. Inspired by echo state networks (ESN), this $k$ESNP model is trained by ridge regression algorithm. Six time series are used as benchmark data sets to evaluate the $k$ESNP model and it is compared with 33 baseline prediction methods. The experimental results demonstrate that the proposed $k$ESNP model is sufficient for the task of time series forecasting.

Our study proposes a novel Parallel Temporal–Spatial-Frequency Neural Network (PTSFNN) for emotion recognition. The network processes EEG signals in the time, frequency, and spatial domains simultaneously to extract discriminative features. Despite its relatively simple architecture, the proposed model achieves superior performance. Specifically, PTSFNN first applies wavelet transform to the raw EEG signals and then reconstructs the coefficients based on frequency hierarchy, thereby achieving frequency decomposition. Subsequently, the core part of the network performs three independent parallel convolution operations on the decomposed signals, including a novel graph convolutional network. Finally, an attention mechanism-based post-processing operation is designed to effectively enhance feature representation. The features obtained from the three modules are concatenated for classification, with the cross-entropy loss function being adopted. To evaluate the model’s performance, extensive experiments are conducted on the SEED and SEED-IV public datasets. The experimental results demonstrate that PTSFNN achieves excellent performance in emotion recognition tasks, with classification accuracies of 87.63% and 74.96%, respectively. Comparative experiments with previous state-of-the-art methods confirm the superiority of our proposed model, which can efficiently extract emotion information from EEG signals.

Video action detection (VAD) is a formidable vision task that involves the localization and classification of actions within the spatial and temporal dimensions of a video clip. Among the myriad VAD architectures, two-stage VAD methods utilize a pre-trained person detector to extract the region of interest features, subsequently employing these features for action detection. However, the performance of two-stage VAD methods has been limited as they depend solely on localized actor features to infer action semantics. In this study, we propose a new two-stage VAD framework called Joint Actor-scene context Relation modeling based on Visual Semantics (JARViS), which effectively consolidates cross-modal action semantics distributed globally across spatial and temporal dimensions using Transformer attention. JARViS employs a person detector to produce densely sampled actor features from a keyframe. Concurrently, it uses a video backbone to create spatio-temporal scene features from a video clip. Finally, the fine-grained interactions between actors and scenes are modeled through a Unified Action-Scene Context Transformer to directly output the final set of actions in parallel. Our experimental results demonstrate that JARViS outperforms existing methods by significant margins and achieves state-of-the-art performance on three popular VAD datasets, including AVA, UCF101-24, and JHMDB51-21.

In this paper, the finite-time passivity (FTP) problem for multi-weighted coupled neural networks (MWCNNs) with directed topologies and time-varying delay is discussed. Firstly, by designing a new state feedback controller, several FTP criteria are given for the considered network. Then, some finite-time synchronization (FTS) criteria are established by employing the FTP results. Secondly, a hybrid impulsive and state feedback controller is first designed, under which different FTP and FTS criteria are presented and the synchronization time is successfully shortened compared to the non-hybrid controller without impulses. Finally, numerical simulations are given to show the effectiveness and superiority of the obtained results.