Search

Trust region policy optimization (TRPO) is one of the landmark policy optimization algorithms in deep reinforcement learning. Its purpose is to maximize a surrogate objective based on an advantage function, subject to the limited Kullback–Leibler (KL) divergence of two consecutive policies. Although there have been many successful applications of this algorithm in the literature, the approach has often been criticized for suppressing the exploration ability of some application environments due to its strict divergence constraint. As such, most researchers prefer to use entropy regularization, which is added to the expected discounted rewards or the surrogate objectives. That said, there is much debate about whether there might be an alternative strategy for regularizing TRPOs. In this paper, we present just that. Our strategy is to regularize the KL divergence-based constraint via Shannon entropy. This approach enlarges the difference between two consecutive policies and thus derives a new TRPO scheme with entropy regularization for use with KL divergence constraint. Next, the surrogate objective and Shannon entropy are approximated linearly, while the KL divergence is expanded quadratically. An efficient conjugate gradient optimization procedure then solves two sets of linear equations, providing a detailed code-level implementation that can be used for a fair experimental comparison. Extensive experiments within eight benchmark environments demonstrate that our proposed method is superior to both the original TRPO and the entropy regularized objective TRPO. Further, theoretical and experimental analysis shows that three TRPO-like methods have an equal time complexity and a close computational burden. [ABSTRACT FROM AUTHOR]

Object detection is one of the core tasks in computer vision that serves as a crucial underpinning for numerous applications. In recent years, deep learning-based methods have achieved remarkable performance in object detection. However, the performance of small objects still remains unsatisfactory. Therefore, some specific architectures have been proposed to address this issue in certain areas, such as remote-sensing and UAV images. In this paper, we aim to design a pluggable and non-intrusive method, termed as PatchDetector, to improve the performance of small object detection, which can effectively avoid the time and resource overhead of retraining the entire network. To achieve that, we first analyze why the mainstream networks perform poorly on small objects and find out that the fundamental reason is that the features of small are superseded by the background, which leads to a significant semantic gap in multi-level layers. Then, significance analysis is conducted to find the essential features for improving the small object detection. Next, with the located significant features, we devise a pluggable patch network for extracting essential features for small objects, which is non-intrusive to the original network. Experiments on mainstream detectors, including YOLO series and Faster RCNN, show that the proposed PatchDetector achieves 0. 4 % ∼ 2. 0 % mAP on small objects while not compromising the performance of medium and large objects. • The first pluggable and non-intrusive patch for small object detection performance. • We analyze the small object poor performance and locate the essential features. • Experiments demonstrate that the PatchDetector achieves 0. 4 % ∼ 2. 0 % mAP on small object. [ABSTRACT FROM AUTHOR]

Salient object refers to the conspicuous objects or regions within an image that stand out prominently from its surroundings. Depth maps are commonly utilized as supplementary inputs for salient object detection, referred to as RGB-D SOD. Due to the diverse acquisition sensors, such as infrared detectors and stereo cameras, the quality of acquired depth maps varies considerably. The low-quality depth introduces noise that seriously reduces detection accuracy. To tackle this problem, a triple attention architecture based on a 3D convolutional neural network tailored for quality-aware salient object detection is proposed in this paper, which capitalizes on the strengths across modality, channel, and spatial dimensions. The modality attention learns the quality factors based on the overall modal features. The channel attention highlights features in the dimension of channels, and the patch-level spatial attention establishes long-range dependencies. Thus, the quality factors, channel differences, and spatial contrast are combined to achieve global and local fusion. To enable the evaluations on low-quality depth maps, an assessment criterion is further introduced to categorize the RGB-D datasets. Experimental results of state-of-the-art methods on different quality levels demonstrate the proposed method's effectiveness, especially for the low-quality depth. • A triple attention framework for quality-aware salient object detection. • Modality, channel, and patch-level spatial attention are effective for saliency detection. • A novel quality assessment criterion for depth maps. [ABSTRACT FROM AUTHOR]

In the research of complex networks, how to find a set of nodes in the network with the most extensive range in the propagation process, i.e., the Influence Maximization (IM) problem, is one of the focal topics. Existing studies mainly consider the information dissemination process on networks and how to select diffusive nodes efficiently, but little attention has been paid to changes related to the network structure. In reality, networked systems are exposed to uncertain interferences and even destructive sabotages, and cascading failures are one common destruction that can cause networks to collapse even if only a small number of nodes fail. In the case of various complex environmental factors, how to select robust and influential nodes, i.e., the robust influence maximization (RIM) problem, is of great importance in promoting the realistic application of the influence maximization problem. This paper investigates the RIM problem under cascading failures to address the shortcomings in previous studies. Based on existing research, a new performance evaluation metric, R S-cf , is designed to assess the level of robust influence in a numerical form. For solving the seed determination problem, a Memetic algorithm towards the RIM problem under cascading failures, MA-RIM CF , is designed to find nodes with stable information propagation capability guided by R S-cf. Experiments have been conducted on both synthetic and realistic networks to validate the performance of the algorithm. Results indicate that MA-RIM CF can obtain competitive candidates over existing approaches, and seeds with robust and influential abilities are generated to solve diffusion dilemmas. [ABSTRACT FROM AUTHOR]

Accurate depth cues are crucial for 3D perception tasks, and monocular depth estimation networks are no longer sufficient for realistic scenarios. Currently, the most effective approaches are to introduce depth information from other modalities into the image. Radar has become a popular sensor for fusion with cameras due to its low price and all-weather working characteristics. This paper aims to explore how to more effectively integrate the heterogeneous data of radar point clouds and RGB images to improve the performance of depth estimation. Most of the previous works have not fully exploited the potential of integrating these two modalities, so we propose RCDformer, a novel network based on the transformer architecture that fuses radar-camera for dense depth estimation. Without reducing the receptive field, our approach can fully model the contextual relationships between sensors to reduce the impact of radar noise on overall performance. With the proposed Radar-guided Multi-scale Depth Fusion (RGDF) module, the prior spatial information mapped by the Radar Feature Extractor (RFE) is embedded into a set of multi-scale hierarchical features output by Image Feature Extractor (IFE) via the modified deformable cross-attention, which aims to guide the depth prediction of images. Furthermore, we discover that incorporating the Radar Cross Section (RCS) attribute as an extended channel for the radar map is beneficial for dense depth estimation, which improves the overall performance of our model. We evaluate the proposed method on the nuScenes dataset, and the experiment results show that our method still achieves significant advantages in most metrics compared to the state-of-the-art models. [ABSTRACT FROM AUTHOR]

The widespread adoption of deep learning is facilitated in part by the availability of large-scale data for training desirable models. However, these data may involve sensitive personal information, which raises privacy concerns for data providers. Differential privacy has been thought of as a key technique in the privacy preservation field, which has drawn much attention owing to its capability of providing rigorous and provable privacy guarantees for training data. Training deep learning models in a differentially private manner is a topic that is gaining traction as this alleviates the reconstruction and inference of sensitive information effectively. Taking this cue, in this paper, we present here a comprehensive and systematic study on differentially private deep learning from the facets of privacy attack and privacy preservation. We explore a new taxonomy to analyze the privacy attacks faced in deep learning and then survey the type of privacy preservation based on differential privacy to tackle such privacy attacks in deep learning. Finally, we propose the first probe into the real-world application of differentially private deep learning, and then conclude with several potential future research avenues. This survey provides promising directions for protecting sensitive information in training data via differential privacy during deep learning model training. [ABSTRACT FROM AUTHOR]

This paper considers the adaptive fixed-time neural tracking dynamic surface control (DSC) for high-order nonlinear switched systems. The uncertain nonlinear functions are approximated by neural networks (NNs). And the obstacles of high-order terms are eliminated by the adding a power integrator. A novel fixed-time convergence filter is proposed to refrain from the problem of repeated differentiation of virtual controllers. On the basis of the backstepping control algorithm and the common Lyapunov function (CLF) method, a novel adaptive fixed-time neural DSC strategy is developed. It is proven that the states in the closed-loop system are bounded and the tracking error converges to an area of zero in fixed time. The simulation experiments further verify the feasibility of the mentioned method. [ABSTRACT FROM AUTHOR]

In the area of neural rendering-based novel view synthesis, illumination is important since shadows cast by objects under various light sources provide indications about their geometries and materials. However, due to high physical device complexity and simulation distortion, large-scale photorealistic multiple illumination multi-view datasets are difficult to obtain. In order to address this problem, a physical-virtual interactive parallel light fields based collection method is proposed in this paper. The physical part of parallel light fields is firstly used to capture 3D models and 2D images of objects under different lights. Then a Reak-to-Sim adaptation module was proposed to enhance realism by estimating material characteristic. Instead of manually setting, the learned resulting material parameters are then utilized to initialize virtual engine blender for subsequent rendering and data collection. Besides, to better handle self-occlusion problem in the acquired parallel light fields dataset, a conditional visibility module is designed in modeling visibility of each sampling point along a sampling ray. Compared with the Neuray, by introducing Conditional Normalizing Flow, visibility are assumed as samples from some distribution due to the fact that visibilities along the ray should be monotonically decreasing and are within the range of [ 0 , 1 ]. The visibility are calculated in a data driven manner, which brings more flexibility. By pretraining the conditional visibility network in parallel light field dataset, experiments demonstrate that more photorealistic inputs improve Peak-Signal-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) by 0.11% and 0.68% in validation dataset NeRF synthesis and LLFF. Besides, compared to Neuray, the proposed conditional visibility module is more flexible and get a PSNR improvement of 0.55 and 0.5 in NeRF synthesis and LLFF dataset, respectively. [ABSTRACT FROM AUTHOR]

Emotions play a large role in interpersonal communication, marketing, healthcare and the service industry. For this reason, much research has been carried out on emotion classification until today. Audio-visual emotion recognition is a field within artificial intelligence and machine learning that focuses on recognizing and understanding human emotions from both visual and audio cues. It combines computer vision and audio processing techniques to analyze and interpret emotional states expressed by individuals. This paper presents a deep learning model developed over an operational neural network using multiple inputs and aimed at audio-visual emotion recognition. The proposed network utilizes both visual and audio information in an end to end approach. The primary objective of this work is to demonstrate that multi-input models can produce more efficient outcomes compared to single-input models in emotion classification. Another objective is to demonstrate the superior performance of weight calculation methods employed in operational neural networks compared to the conventional weight calculation methods used in convolutional neural networks. Therefore, we want to demonstrate that substituting convolutional neural network approaches with operational neural network methods can yield superior outcomes in emotion categorization models. In the proposed architecture, regular convolutional layers are replaced with operational layers. The experimental results demonstrate that the operational convolutional architecture performs better compared to the classical convolutional neural network architecture. [ABSTRACT FROM AUTHOR]

Graph Neural Networks (GNNs) have exhibited significant success in various applications, but they face challenges when labeled nodes are limited. A novel self-supervised learning paradigm has emerged, enabling GNN training without labeled nodes and even surpassing GNNs with limited labeled data. However, self-supervised methods lack class-discriminative node representations due to the absence of labeled information during training. In this paper, we exploit a supervised graph contrastive learning approach (SGCL) framework to tackle the issue of limited labeled nodes, ensuring coherent grouping of nodes within the same class. We propose augmentation techniques based on a novel centrality function to highlight important topological structures. Additionally, we introduce a supervised contrastive learning method that removes the necessity for negative samples and simplifies complex elements effortlessly. Our approach combines supervised contrastive loss and node similarity regularization while achieving consistent grouping of unlabeled nodes with labeled ones. Furthermore, we utilize the pseudo-labeling technique to propagate label information to distant nodes and address the underfitting problem, especially with low-degree nodes. Experimental results on real-world graphs demonstrate that SGCL outperforms both semi-supervised and self-supervised methods in node classification. [ABSTRACT FROM AUTHOR]

The detection of infrared moving small objects faces significant challenges in the field of object detection for air vehicles. These types of objects usually occupy a small number of pixels in an infrared image, resulting in limited feature information, considerable feature loss, low recognition accuracy, and various challenges in single-frame detection. To address these challenges, this paper proposes an efficient multi-input method named Multi-YOLOv8, which is based on the YOLOv8s model. The proposed method uses current frames as a primary input and incorporates optical flow processing images and background suppression images as auxiliary inputs to improve detection performance. In addition, an improved method is developed for optical flow computations, named the pyramidal weight-momentum Horn–Schunck (PWMHS) method, which can process optical flows efficiently and precisely. An improved version of the Wise-IoU (WIoU) v3, referred to as α* -WIoU v3, is proposed as a bounding box regression (BBR) loss function to optimize the YOLOv8 network. Further, the BiFormer module and lightweight convolution GSConv are introduced to improve the attention to key information for the objects and balance the computational cost and detection performance, respectively. Moreover, a small object detection layer is added the YOLOv8 network to improve the capability for small object detection. Finally, a warming-up training method that can reduce the dependency on auxiliary inputs and ensure model stability in case of auxiliary input failures is developed. The results of the comprehensive experiments on an open-access dataset reveal that the proposed model outperforms the mainstream models in overall performance. The proposed method can significantly enhance the detection ability of infrared moving small objects. [ABSTRACT FROM AUTHOR]

Temporal knowledge graphs (TKGs) are still far from completeness although they have benefited many artificial intelligence applications successfully. To alleviate the incompleteness of TKGs, temporal knowledge graph completion (TKGC) aims to perform link prediction and reason new time-sensitive facts from existing facts. Among the various TKGC methods, temporal knowledge graph embedding (TKGE) methods represent entities, relations, and timestamps in low-dimensional spaces, which are known for their high reasoning performance and robust scalability. Some previous researches on TKGE aim to endow the embedding quadruple with the translational characteristic by modeling the global relationship in the embedding quadruple. However, the weights of same dimensional entries of the embedding quadruple are fixed and unique, which limits the ability to capture diverse global relationships. Besides, most TKGE models view timestamps as a kind of general feature and overlook their interrelations and correlations with the queries. Moreover, the distinct characteristics of an entity as the subject entity and the object entity of facts have not been fully leveraged. In this paper, we propose a query-aware embedding model based on the convolutional neural network (CNN) named ConvTKG to perform TKGE, thus tackling the TKGC task. We design a new temporal information encoder based on the Gated Recurrent Unit (GRU) and attention mechanism to learn the query-aware representation of temporal information. More importantly, we utilize a CNN-based decoder where multiple one-dimensional convolution kernels are operated on the matrix composed of entity embedding, relation embedding, and temporal representation to capture global relationships among them. In addition, we assign two independent vectors for each entity and take advantage of the inverse relation to allow them to be learned dependently. Experiments show that ConvTKG achieves better link prediction performance than previous state-of-the-art baseline methods for TKGC on three benchmark datasets: ICEWS14, ICEWS05-15, and GDELT. • We propose the first weight-adaptive TKGE model with translational characteristic. • We introduce a new query-aware timestamp encoding method for TKGC. • Two dependent embedding vectors for each entity capture its distinct semantics. • Experiments demonstrate the effectiveness of ConvTKG on three TKGC benchmarks. [ABSTRACT FROM AUTHOR]

Multi-label text classification (MLTC) is the process of establishing relationships between documents and their corresponding labels. Previous research has focused on mining textual information, treating labels as information-less vectors in classification. This ignores the semantic and dependency relationships of labels. In real-life scenarios, the neglect of label information contradicts the classification process, which presents significant challenges for MLTC tasks. Label embedding partially resolves label information loss. Efficiently exploring semantic and dependency relationships of labels and their text connections remains a new challenge. In this paper, we propose a Label-Text Bi-Attention Capsule Networks (LTBACN) model for in-depth exploration of the dependency relationships between labels and text. Specifically, we first incorporate label information into nodes through label embedding, construct a graph structure to represent the dependency relationships between labels, and use Graph Convolutional Networks (GCN) to propagate information between nodes to further mine the relationships between labels. Subsequently, we employ a label-text bi-attention mechanism to learn the feature relationships between labels and text. The label-to-text attention mechanism extracts label-relevant text representations, while the text-to-label attention mechanism extracts the most relevant label representations for the text. We then merge these two types of feature representations to obtain fused representations that incorporate label-text bi-directional information. Finally, the fused features are fed into a capsule network classifier to capture multi-level semantic information and match the corresponding labels. The experimental results demonstrate that LTBACN outperforms other methods in terms of classification effectiveness. Compared to state-of-the-art methods, LTBACN achieves a significant improvement of 0.41%–0.68% in M i c r o − F 1 measure, 0.52%–3.26% in M a c r o − F 1 measure, 0.32%–2.18% in P @ k measure, and 0.01%–1.18% in n D C G @ k measure on the AAPD and RCV1-v2 datasets. [ABSTRACT FROM AUTHOR]

In the paper, a new approach is presented to tackle an interval optimization problem with nonconvex interval objective function and affine interval equality and inequality constraints utilizing a recurrent neural network. The approach involves converting the nonconvex interval quadratic programming into a cubic optimization via convex combinations and considering its weight as a decision variable. The recurrent neural network is then established to solve the cubic optimization through subgradient techniques and an exterior penalty function method. Moreover, it is proven that there is a unique global solution to the recurrent neural network, and its trajectory can reach the feasible region in a finite time and remain there. Additionally, it is demonstrated that the trajectory of recurrent neural network converges exponentially or in finite time towards a singleton belonging to the set of critical points of the cubic optimization. This approach is beneficial for interval quadratic programming problems where the weight is unknown or challenging to determine in practical applications. Finally, the effectiveness of this approach is verified through two numerical examples. • (i) The weight is first regarded as the decision variable in the nonconvex interval quadratic programming. Unlike traditional algorithms that preset weights. This approach not only facilitates finding the optimal solution when weights are difficult to determine in practice but also accommodates scenarios with predetermined weights. • (ii) The nonconvex interval quadratic programming is converted into nonconvex cubic optimization by the parameter representation of intervals, and the recurrent neural network is first used to solve the nonconvex cubic optimization. • (iii) The behavior of recurrent neural networks is proven to converge exponentially or in finite time to a singleton belonging to the set of critical points of the cubic optimization, extending previous findings in quadratic programming. [ABSTRACT FROM AUTHOR]

Visual Question and Answering is a fast-evolving field of research where we attempt to answer the question based on an image as a context. In this paper, we try to add support for answering questions that are based on emotions with face detection and basic emotion extraction. With the basic emotions, we further try to find out compound emotions to expand the area of answerable questions. We complete the said operations in two stages: i) Caption generation. ii) Question and answering with that caption as context. The context generation process can be further divided into i) general caption generator ii) emotional caption generator. In general caption generator, we try to find a single sentence providing a basic information about the input context image, using an Attention [9] based model. In the later phase, the emotional caption generator finds the information of the emotions of the faces of the image using RetinaFace [20] and DeepFace [1]. In emotional caption generator, apart from basic emotion generation, we also try to find compound emotions depicted by each of the faces by learning the patterns in facial landmarks generated by MediaPipe [7] with CNN based architecture. In this module, we also generate a set of know question and answers to use in the next phase. As for the question and answering part, we first use BERT [4] for finding an answer, given a question and the captions generated as context of the question. If the confidence of answer exceeds a threshold value, we report that answer as final. If not, we try to find the known question similar to the asked question. The answer generated then is the final answer. • Questions based on emotions are difficult to answer with only image as context. • The focus is on questions based on emotions. • A contribution to the limited work done on compound emotion classification. • Facial landmark identification using MediaPipe for compound emotion classification. • Paraphrase identification with Random Forest for finding similar known question. [ABSTRACT FROM AUTHOR]

Recently, graph-based deep learning models have exhibited remarkable performance in generating solution expressions for the math word problem (MWP). However, most of these models have not taken into account the limitations and errors in constructing prior knowledge graphs, which may affect their accuracy and reliability in practical applications. In addition, during graph learning, they focus on extracting information from each given graph, while neglecting the adaptability and unification of graph representation learning. In this paper, we propose a novel multi-view graph learning-to-tree model with dual-strategy (MVG-DS-T), in which it performs adaptive and consistent multi-view representation learning through two benchmark graphs. Specifically, we construct benchmark graphs via semantic dependency parsing of MWP text, considering both semantic and quantitative aspects, i.e., semantic graph and quantitative graph. Then, the reconstruction strategy is employed to reconstruct the structure of the benchmark graphs to capture the adaptive representation information suitable for downstream tasks, while the alignment strategy is utilized to overcome the limitation of independent view representations by unifying the semantic and quantity embedding information through graph structure. Also, an adaptive length normalized loss balancing term for the tree-based decoder is introduced to control the model focus on label length during training, resulting in better equation generation. Extensive experiments demonstrate the effectiveness of the proposed approach on the MWP task. The empirical results show that MVG-DS-T achieves performance comparable to that of the state-of-the-art graph-based models in the existing literature. [ABSTRACT FROM AUTHOR]

Combinatorial optimization problems (COPs) play an important role in both industrial production and theoretical research. As a classical class of optimization algorithms, evolutionary algorithms have shown good performance in COPs. However, as the size of the problem increases, it becomes difficult for evolutionary algorithms to produce satisfactory solutions within the specified time. In recent years, neural network algorithms have been applied to solve COPs and have shown superior effects. Inspired by this, this paper proposes a new algorithm based on graph structure for solving COPs. Through relaxation, COPs are transformed into their corresponding continuous optimization problems. The output state of our algorithm is converted to a discrete solution by approximation method. Compared with previous algorithms, our algorithm can not only solve COPs with general form such as binary quadratic programming (BQP), but also solve COPs with special form, which greatly expands the application scope of neural network algorithms. In addition, our algorithm can be embedded into other problem frameworks such as solving multi-objective combinatorial optimization problem (MOCOP) through scalarization method. A new penalty function is added to the objective function, which enables our algorithm to overcome the inconsistency between the optimal solution of the original problem and the corresponding continuous problem, so that our algorithm can perform well on various problems. Several numerical simulations are used to illustrate the effectiveness of our algorithm in solving COPs. Experimental results show that our algorithm can effectively solve COPs with general form and has a shorter solving time compared to traditional evolutionary algorithms. [ABSTRACT FROM AUTHOR]

Capturing images with incorrect exposure settings fails to deliver a satisfactory visual experience. Only when the exposure is properly set, can the color and details of the images be appropriately preserved. Previous exposure correction methods based on convolutions often produce exposure deviation in images as a consequence of the restricted receptive field of convolutional kernels. This issue arises because convolutions are not capable of capturing long-range dependencies in images accurately. To overcome this challenge, we can apply the Transformer to address the exposure correction problem, leveraging its capability in modeling long-range dependencies to capture global representation. However, solely relying on the window-based Transformer leads to visually disturbing blocking artifacts due to the application of self-attention in small patches. In this paper, we propose a CNN Injected Transformer (CIT) to harness the individual strengths of CNN and Transformer simultaneously. Specifically, we construct the CIT by utilizing a window-based Transformer to exploit the long-range interactions among different regions in the entire image. Within each CIT block, we incorporate a channel attention block (CAB) and a half-instance normalization block (HINB) to assist the window-based self-attention to acquire the global statistics and refine local features. In addition to the hybrid architecture design for exposure correction, we apply a set of carefully formulated loss functions to improve the spatial coherence and rectify potential color deviations. Extensive experiments demonstrate that our image exposure correction method outperforms state-of-the-art approaches in terms of both quantitative and qualitative metrics. [ABSTRACT FROM AUTHOR]

The Wasserstein distance in the optimal transport (OT) model is being widely used in machine learning applications due to its mathematical and geometric properties. Since the entropy regularized OT is a convex problem, and for its large-scale problems, many algorithms have been proposed. Existing methods mainly adopt iterative random projection techniques to approximate the Wasserstein distance in the OT model. In this paper, we employ the entropic domain decomposition algorithm with mini-batch learning to calculate the entropy regularized OT problem and investigate the stability of this algorithm. The algorithm performs on different cells of the domain instead of using the projection technique and it is based on a mini-batch loss function. The corresponding solution in each iteration is derived from the dual problem of entropy regularized OT on each decomposed cell. Once the solutions to the dual problem on all decomposed cells are obtained, the corresponding transport plan in each iteration can be obtained. We show that the transport plan computed by its dual variables is admissible, and we also give the sub-gradient approximation result. In addition, we exploit the statistical concentration result of the subsampled mini-batch Wasserstein distance on decomposed cells. Finally, the numerical experiments validate that the proposed algorithm can save computational time further. [ABSTRACT FROM AUTHOR]

Within the realm of computer vision, the landscape has been significantly reshaped by the abundance of extensive and diverse datasets, leading to remarkable breakthroughs in image processing. These advancements have reverberated across a wide spectrum of applications, catalyzing transformative outcomes. However, in stark contrast, the field of digital rock analysis finds itself grappling with a conspicuous dearth of data, a challenge that casts a formidable shadow over the effective deployment of computer vision techniques for rock image analysis. In response to this pressing issue, this paper presents a pioneering methodology designed to surmount the hurdles posed by data limitation in the realm of digital rock analysis. At the core of this innovative approach lies the fusion of artificially generated digital rock images, created using a state-of-the-art diffusion model, with their authentic counterparts. This fusion is guided by the overarching objective of augmenting the efficacy of various digital rock analysis applications. This integration endeavors to bridge the gap between the limited available data and the substantial demands of the digital rock analysis domain. The practical significance and potential of this integrated approach are vividly demonstrated through a series of concrete implementations. These include, but are by no means limited to, enhancing image quality to facilitate clearer visualization of intricate rock structures and refining the estimation of petrophysical properties with increased accuracy. [ABSTRACT FROM AUTHOR]

Representing the scenes by learning the subtle variations in the spatial content of different classes is crucial for scene classification in remote sensing images. In this paper, we propose a scene attribute modeling to obtain a discriminative and compact representation for scene classification. First, we construct a scene attribute model (SAM) by training a Gaussian mixture model (GMM) using convolutional features to capture the scene attributes implicitly. Then, we perform a maximum a posteriori (MAP) adaptation to enhance the contribution of significant attributes in each scene resulting in a high-dimensional feature vector which contains redundant attributes from all the scenes. Hence, we use factor analysis to obtain a compact representation of the high-dimensional feature vector termed scene-vector , which retains only the significant attributes specific to a scene. The proposed approach is demonstrated on three benchmark datasets, namely, UC Merced Land Use, AID, and NWPU-RESISC45 datasets. We further show that, being a compact representation, our scene-vector outperforms state-of-the-art methods for scene classification in remote sensing images. [ABSTRACT FROM AUTHOR]

In this paper, an enhanced structural developmental neural network with information saturation (ESDNNIS) is proposed for continual unsupervised learning. It improves SDNNIS in the following respects: (1) it makes a distinction between the developmental stages of neurons to better regulate the updating of neurons; (2) it adopts the forgetting mechanism to control the network size; (3) it changes the way coverage domain parameter is initialized and updated to divide clusters more accurately; and (4) it adds a parent–child relationship update mechanism to provide better robustness to sample input order. ESDNNIS inherits the unsupervised incremental learning and class segmentation capabilities of SDNNIS, and achieves better class incremental clustering for more complex datasets while using fewer neurons than SDNNIS. The experimental results show that the accuracy of clustering results of ESDNNIS is improved by 10.94% on average compared with SDNNIS, while the number of generated neurons is reduced by 71.93% on average. [ABSTRACT FROM AUTHOR]

Gradient-based algorithms are still popularly used for training radial basis function neural network (RBFNN). However, these algorithms may lead to the vanishing gradient (saddle point or local minimum) problem, which is one of the common problems that limit learning performance. To cope with this, a hybrid hyperplane gradient learning algorithm (HHGLA) is proposed to improve the learning performance of the RBFNN in this paper. First, a hyperplane gradient (HPG), based on a hyperspace constructed by a solution population (SP), is introduced. Thus, the search process can cross the surface of the cost function to avoid the appearance of vanishing gradient. Second, an adaptive learning rate is designed to restrict the search process into this hyperspace. Then, during the learning process, the hyperspace is constantly contracted to approximate the global optimal solution. Third, the convergence property of HHGLA-based RBFNN is thoroughly analyzed to ensure its application success. Finally, empirical comparisons of the proposed HHGLA-RBFNN are given to illustrate its superiority. The simulation results show the feasibility of HHGLA-RBFNN of accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we investigate intra-layer synchronization in multiplex networks via pinning control strategies. All layers have different topologies and different intrinsic node dynamics. Novel sufficient criteria are derived for pinning intra-layer synchronization of multiplex networks, which indicates that the pinned node set can stabilize the multiplex network if, for each layer, the pinned node(s) can access all unpinned nodes. A distributed adaptive algorithm and finite-time pinning algorithm for intra-layer synchronization of multiplex networks are also proposed. Finally, we give some numerical examples to validate the effectiveness of these theoretical results. [ABSTRACT FROM AUTHOR]

The task of motion prediction is pivotal for autonomous driving systems, providing crucial data to choose a vehicle behavior strategy within its surroundings. Existing motion prediction techniques primarily focus on predicting the future trajectory of each agent in the scene individually, utilizing its past trajectory data. In this paper, we introduce an end-to-end neural network methodology designed to predict the future behaviors of all dynamic objects in the environment. This approach leverages the occupancy map and the scene's motion flow. We are investigating various alternatives for constructing a deep encoder–decoder model called OFMPNet. This model uses a sequence of bird's-eye-view road images, occupancy grid, and prior motion flow as input data. The encoder of the model can incorporate transformer, attention-based, or convolutional units. The decoder considers the use of both convolutional modules and recurrent blocks. Additionally, we propose a novel time-weighted motion flow loss, whose application has shown a substantial decrease in end-point error. Our approach has achieved state-of-the-art results on the Waymo Occupancy and Flow Prediction benchmark, with a Soft IoU of 52.1% and an AUC of 76.75% on Flow-Grounded Occupancy. [ABSTRACT FROM AUTHOR]

U-Net, known for its simple yet efficient architecture, is widely utilized for image processing tasks and is particularly suitable for deployment on neuromorphic chips. This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. To address the issue of information loss, we introduce multi-threshold spiking neurons, which improve the efficiency of information transmission within the Spiking-UNet. For the training strategy, we adopt a conversion and fine-tuning pipeline that leverage pre-trained U-Net models. During the conversion process, significant variability in data distribution across different parts is observed when utilizing skip connections. Therefore, we propose a connection-wise normalization method to prevent inaccurate firing rates. Furthermore, we adopt a flow-based training method to fine-tune the converted models, reducing time steps while preserving performance. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart, surpassing existing SNN methods. Compared with the converted Spiking-UNet without fine-tuning, our Spiking-UNet reduces inference time by approximately 90%. This research broadens the application scope of SNNs in image processing and is expected to inspire further exploration in the field of neuromorphic engineering. The code for our Spiking-UNet implementation is available at https://github.com/SNNresearch/Spiking-UNet. [ABSTRACT FROM AUTHOR]

The realm of aspect-based sentiment analysis (ABSA), which delves into the nuanced sentiment expressions individuals hold towards specific services or products, has demonstrated immense potential in real-world applications. Recently, ABSA has evolved into the development of aspect-based sentiment quadruple extraction (ASQP). ASQP's objective is to predict four crucial sentiment elements: aspect , sentiment , opinion and category , where such comprehensive approach paints a holistic description of sentiment, facilitating downstream applications. However, prevailing ASQP models suffer from various limitations, such as inefficiency in decoding, inadequate handling of implicit aspects and opinions, and underutilization of structural information. In this paper, we explore an innovative approach to enhance ASQP. Firstly, we adopt a pointer-based non-autoregressive generative framework, enabling the parallel generation of all sentiment quadruples. This approach preserves the advantages of generative methods while significantly boosting decoding efficiency. Additionally, we introduce latent variable learning to model the aspect and opinion elements, effectively enhancing our ability to reason about implicit ASQP components. Furthermore, we propose an aspect-and-opinion-guided latent structure to bolster sentiment-aware context learning. This dynamically induced graph structure adapts to the specific requirements of the task, offering optimal support for ASQP. Our method outperforms current state-of-the-art models on four benchmark ASQP datasets, demonstrating its significant superiority. A detailed analysis highlights the benefits of non-autoregressive decoding in achieving high inference efficiency, the effectiveness of the variational module in capturing implicit sentiment elements, and the value of the dynamically induced latent structure in accurate sentiment feature learning. Moreover, our system excels in producing interpretable predictions. • We for the first time model the task of aspect-based sentiment quadruple extraction (ASQP) with a non-autoregressive generative paradigm with a pointer network, generating all the sentiment quadruples in parallel, By this, we keep the advantage of the generative scheme meanwhile advancing in high decoding efficiency. • We propose to model the aspect and opinion elements as latent variables, effectively enhancing the learning of implicit ASQP elements via unsupervised aspect-opinion reasoning. • We introduce an aspect&opinion-guided latent structure to aid the sentiment-aware context learning, which is dynamically induced according to the end task's need for offering the best helpfulness. • Our framework outperforms the current best-performing baseline systems on the benchmark datasets of ASQP. Further in-depth analyses are conducted for a better understanding of our method. [ABSTRACT FROM AUTHOR]

In this paper, we explore the stabilization problem of discrete-time Markov jump linear systems from a new perspective. We establish a novel learning-based framework that combines control theory and learning methods to design stabilizing feedback gains. Firstly, we reformulate the stabilization problems for discrete-time Markov jump linear systems into finite-time counterparts. Subsequently, leveraging techniques from the field of learning, we effectively and efficiently solve the finite-time stabilization problems. We systematically investigate two typical stabilization problems of discrete-time Markov jump linear systems within the proposed framework, namely the detector-based feedback stabilization and the static output feedback stabilization problems. Extensive simulation on various numerical examples demonstrates the advantages of our approach over several existing methods for discrete-time Markov jump linear systems. [ABSTRACT FROM AUTHOR]

Recently, graph collaborative filtering has been proposed as a superior recommendation technique, due to its outstanding capability of capturing high-order correlations from user–item interactions. Despite effectiveness, it still suffers from two limitations on representation learning: (1) imbalanced data distribution. User/item nodes with high-degree usually interfere with the representation learning process of low-degree nodes, deteriorating the recommendation accuracy; (2) structural noise vulnerability. The neighborhood aggregation scheme for the node representing could easily amplify structural noises, damaging the robustness of recommenders. The latest studies have made progress in overcoming the two limitations by capturing self-supervision signals via contrastive learning. Nevertheless, they somehow rely on heuristics to design, at a certain distance from a more comprehensive settlement. To make contrastive learning more entrenched with graph collaborative filtering, this paper proposes a multi-task framework JCG that integrates joint contrastive learning strategies with a backbone of graph-based recommender. Specifically, (1) we design six contrastive learning tasks categorized as structural and semantic, and obtain nine joint strategies by combining two tasks from each category; (2) we systematically study the effect of joint strategies on graph collaborative filtering, finding that JCG with feasible strategies could achieve up to 18.5% and 17.9% performance gain over the backbone on datasets of Yelp and ML, respectively; (3) performance comparison with other competitive baselines demonstrates the superiority of our JCG, especially that on mitigating the two limitations of data imbalance and noise vulnerability. We hope that our conclusion could provide new insight for future studies. [ABSTRACT FROM AUTHOR]

As one of the key research topics of scientific text mining, relation extraction for scientific text has received great attention. Unfortunately, existing scientific relation (SRE) suffers from the pipeline extraction scheme and under-exploration of structural interactions, thus hindering the improvement of task performance. In this paper, we introduce an end-to-end SRE model that effectively addresses these challenges. Our approach first conceptualizes the task as a grid-tagging paradigm, enabling the extraction of all entities, attributes, and relations in a single step. Additionally, we incorporate syntactic dependency structure features into the task. To achieve this, we devise a novel label-aided graph convolutional network model, which simultaneously encodes both the topological structure and edge label features for best resolving the long-range dependence issue. Moreover, we propose two interactive learning mechanisms: intra-structure argument correlation and inter-structure argument correlation. These mechanisms significantly enhance the modeling of interactions within and between relational triplet structures, effectively improving the task performance. Empirically, our system outperforms existing methods and achieves new state-of-the-art performances on two benchmark datasets. Further in-depth analyses are shown to shed light on our approach's strengths. • We for the first time propose an end-to-end framework for the Scientific Relation Extraction task with a grid-tagging scheme. This advancement facilitates the construction of high-performance, high-quality scientific knowledge graphs. • We introduce the integration of semantic dependency structure features and devise a novel label-aided graph convolutional network model to simultaneously capture topological structure and edge label features, effectively addressing long-range supervision challenges. • We devise two interactive learning mechanisms, which significantly enhance the modeling of interaction within and between the relational triplet structures, resulting in improved performance. [ABSTRACT FROM AUTHOR]

The mainstream Multi-Agent Reinforcement Learning (MARL) methods introduce the teammate modeling or the communication mechanism into Centralized Training Decentralized Execution (CTDE) paradigm, which can improve coordination performance. However, the existing teammate modeling methods predict either actions or local observations, limiting their applicability. In addition, the traditional communication mechanism only considers the quantity of the communication links while ignoring the quality of retained communication links, leading to inefficient and redundant communication. To solve the above problems, this paper proposes a novel Multi-Agent Cooperative Strategy with Explicit Teammate Modeling and Targeted Informative Communication (MACS), which can generate and send the more informative message with the higher communication efficiency, further improving the coordination performance. Specifically, the Variational Auto-Encoder (VAE) is leveraged to allow each agent to simultaneously predict the observations and actions of teammates, thus generating more comprehensive communication message. Then, we propose a new Mutual Information (MI) between the communication message and teammate Q-value, which can obtain the informative message, ensuring the exploration and stability of the method. In addition, a targeted dynamic informative communication graph is established by the Graph Neural Network (GNN) which can reduce the redundant communication link through hypothetical analysis, further improving the overall communication efficiency. Eventually, we conduct experiments in StarCraft II, Collaborative Navigation, and Multi-Target Multi-Sensor Coverage environments. Experimental results show that the proposed approach is superior to the state-of-the-art in terms of coordination performance and communication efficiency. [ABSTRACT FROM AUTHOR]

As an important foundational task in the field of natural language processing, the Chinese named entity recognition (NER) task has received widespread attention in recent years. Self-distillation plays a role in exploring the potential of the knowledge carried by internal parameters in the BERT NER model, but few studies have noticed the impact of different granularity semantic information during the distillation process. In this paper, we propose a multi-level semantic enhancement approach based on self-distillation BERT for Chinese named entity recognition. We first design a feasible data augmentation method to improve the training quality for handling complex entity compositions, then construct a boundary smoothing module to achieve the model's moderate learning on entity boundaries. Besides, we utilize the distillation reweighting method to let the model acquire balanced entity and context knowledge. Experimental results on two Chinese named entity recognition benchmark datasets Weibo and Resume have 72.09% and 96.93% F1 scores, respectively. Compared to three different basic distillation BERT models, our model can also produce better results. The source code is available at https://github.com/lookmedandan/MSE. [ABSTRACT FROM AUTHOR]

Federated learning, a privacy-preserving collaborative machine learning paradigm, has led to the proposal of various incentive mechanisms to encourage active participation of data owners. However, most of the existing mechanisms focused on the monopsony market scenario, where only one server-side entity (buyer) is involved. In real-world scenarios, multiple server parties may express simultaneous interest in the data of a client (seller), leading to a non-monopoly market. This paper aims to bridge this gap by introducing the concept of incentivizing federated learning in a non-monopoly market and presents a non-monopoly federated learning incentive mechanism, coined as NmFLI. NmFLI employs a double-auction mechanism to implement federated learning incentives and utilizes the Vickery–Clarke–Groves (VCG) mechanism to ensure client trustworthiness. Additionally, NmFLI devises a method for measuring data quality by calculating the value of clients based on their historical performance, which effectively balances accuracy and computational complexity. We demonstrate that NmFLI possesses properties such as individual rationality and strategy-proofness. Experimental results indicate that NmFLI can effectively incentivize federated learning and achieve higher accuracy than baseline models across various scenarios. For example, when the objectives of various tasks overlap, NmFLI outperforms the best baseline by 3.09% with imbalanced client data while maintaining the same data size. Moreover, NmFLI surpasses the best baseline by 6.12% with different amounts of client data. [ABSTRACT FROM AUTHOR]

The expensive optimization problem, widespread in real-world applications, poses great challenges to traditional evolutionary algorithms (EAs) due to its costly evaluations. A lot of investigations have proved that it is a practical way to incorporate surrogate models into EAs to reduce the number of time-consuming evaluations. Although various types of surrogate models from the community of machine learning, such as regression models that approximate the fitness values of candidate solutions or classification models that predict candidate solutions' category, have been widely applied separately, none of them consistently outperforms the other. Considering the intrinsic consistency of alleviating computational burden to improve the optimization efficiency, this paper introduces a two-layer architecture to integrate regression and classification models and synergize global and local evolution for high-dimensional expensive many-objective optimization problem (EMaOP). To implement this idea, the Kriging model based on incremental learning is utilized to explore the potential promising space. Further, multi local support vector machine (SVM) classifiers assisted improved differential evolution is run by turn with the global search to accelerate convergence. Accordingly, a novel surrogate-assisted EA, named Classification- and Regression-assisted evolutionary algorithm (CR-SAEA), is proposed on this basis. Experimental studies on several benchmark functions with up to 11 objectives and 200 dimensions confirm the effectiveness of the proposed algorithm and its competitiveness against state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

The paper studies the event-triggered passivity and synchronization problems for multiple derivative coupled reaction–diffusion neural networks. Two types of multiple derivative coupled reaction–diffusion neural networks, with and without time-varying delay, are considered. According to the characteristics of multiple derivative coupled reaction–diffusion neural networks, an event-triggered condition is constructed. By imposing appropriate Lyapunov functionals and inequality techniques, several passivity conditions are established for these two networks under the designed event-triggered controllers. Then, synchronization criteria of these two networks are derived based on the relationship between output-strict passivity and synchronization. Moreover, the non-occurrence of the Zeno behavior in the proposed control is proved. Numerical example is illustrated to verify the effectiveness of the proposed criteria. Finally, theoretical results and the associated image encryption application are validated through numerical simulations and statistical analyses. [ABSTRACT FROM AUTHOR]

Graph sampling is a challenging problem in network analysis due to the complex structures of networks. Currently, a series of graph sampling algorithms based on random walks achieve good results in graph sampling tasks. However, the existing methods often reduce the conductance of graphs, causing the sampler to stay in the same node for a long time. This results in undersampling. In this paper, we propose a novel Weighted Jump Random Walk (WJRW) algorithm to generate representative samples. We design a parameter in the WJRW algorithm that can adjust the proportions of random walk and random jump in every step. According to the issue of repeated sample nodes in the Generalized Maximum Degree (GMD) method and the problem of large deviations in the Simple Random Walk (SRW), WJRW addresses the weaknesses of the GMD method and enhances the diffusion of a random walker on graphs, leading to a more representative sample. Then, WJRW addresses the issue of large deviations in SRW and enhances the efficiency of the unbiased estimator. By generating smoother stationary distributions. Numerical experiments with extensive real-world networks verify that our method achieves higher accuracy than classical and state-of-the-art methods in estimating distribution estimation. [ABSTRACT FROM AUTHOR]

The advancement of low-cost, non-manually labeled big data technologies for fault detection in wind turbines is crucial to guarantee their safe and efficient operation. In this context, Normal Behavior Modelling (NBM) is a prevalent approach. However, existing NBM methods for wind turbine fault detection inadequately utilize complex spatial–temporal correlations within the Supervisory Control and Data Acquisition (SCADA) during the normal behavior prediction stage. To cope with this limitation, this paper propose a hierarchical spatial-temporal autocorrelation graph neural network method for online wind turbine pitch system fault detection. This approach integrates a dynamic graph network with an adaptive structure for spatial correlation learning and a transformer model with autocorrelation attention to identify periodic time-distance correlations. Furthermore, a hierarchical neural network, specifically designed for wind turbine physical structure, enhances local information extraction through seven latent graph neural networks and a probsparse attention mechanism. The proposed method demonstrates significant effectiveness in real-world applications, as evidenced by data from a Shanghai wind farm. [ABSTRACT FROM AUTHOR]

Uncertainty estimation is a critical component of building safe and reliable machine learning models. Accurate estimation of uncertainties is essential for identifying and mitigating potential risks and ensuring that machine learning systems operate reliably in real-world scenarios. Various approaches, such as ensemble and Bayesian neural networks have been developed by sampling probability predictions from submodels, which is computationally expensive. At present, these techniques are incapable of precisely delineating the boundary separating in-distribution (ID) and out-of-distribution (OOD) data. To fill up this research gap, this paper presents a normalizing flow based framework to directly predict parameters of prior distributions over the probability with a neural network, the proposed model is able to effectively differentiate between ID and OOD data in regression problems. The posterior distributions learned by the model precisely represent uncertainties for OOD data based solely on ID data, without the need for OOD data during training. This approach has shown promising results in a number of applications, including image depth estimation and image adversarial attacks. [ABSTRACT FROM AUTHOR]

Effective animal intelligent monitoring is of great value in terms of ecological protection and endangered specie conservation. At present, computer vision technologies have shed light on animal intelligent monitoring. Especially, numerous deep learning-based models and methods have been developed to address various challenges, and have made substantial strides in this field. However, there are still several problems to be solved and related areas to be mined, such as exploring new strategies to enhance the robustness and generalization ability of models, designing novel models for complex environments, and establishing large-scale publicly available animal datasets for performance verification of models. Therefore, we comprehensively elaborated and analyzed existing works on animal intelligent monitoring based on advanced information science technologies, so as to provide useful information assistance for relevant researchers. In this paper, we focus on three primary task fields: precise animal localization, tracking and individual identification. Specifically, we elucidate the definition and significance of each monitoring task, and summarize the baseline models for addressing different problems. We provide a specific analysis of strategies and prototypes of the models and methods employed in each tasks following by the technical progression from traditional machine learning to deep learning. In addition, we make a comparison and analysis of the relevant methods, summarize their similarities and differences between them, and point out the advantages and disadvantages of these methods. Finally, we present several unresolved challenges and problems in animal intelligent monitoring and provide potential research directions in the future. We expect that our review can serve as reference and guidance for related research fields. [ABSTRACT FROM AUTHOR]

Image classification is a hot topic in computer vision tasks. As a simple unsupervised network model, auto-encoder can learn and apply features to classification. However, due to the lack of prior knowledge of auto-encoder, there are significant limitations in their performance in practical applications. On the contrary, although precise labels can guide supervised learning to learn accurately, it is difficult to obtain strong supervised information on many tasks because of the high cost of data annotation. In this paper, we propose a weakly-supervised auto-encoder via energy regularization and soft multi-label learning on k labeled samples (WSAE), where weakly-supervised learning not only reduces the workload of manual labeling but also introduces supervised information, which improves the performance of auto-encoder to a large extent. Specifically, we first explore a lower bound value of training data that needs to be labeled in weakly supervised learning. Then, we discriminate the visual consistency of k labeled samples compared to unlabeled samples with soft multi-label to efficiently increase the difference of features between classes and reduce the variation of features within classes for more discriminative feature representations and higher classification accuracy. In addition, an energy regularization is introduced to the model to fit the probability distribution of the data so that the smaller the energy, the more concentrated the probability distribution and the more ordered the system. The model with energy regularization can represent the data better, thereby improving the feature extraction ability and increasing the classification accuracy of the network. Extensive experiments are conducted on some publicly available datasets and demonstrate that our method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper studies the fixed-time containment of the second-order nonlinear multi-agent system (MAS) accompanied by switching topologies and event-triggered communication. The agent is subjected to unknown nonlinear dynamics. A fixed-time RBF observer was constructed based on information obtained from neural networks and event-triggered communication. By combining the controller with the identification information from the observer, it is demonstrated that the system can achieve practical fixed-time output feedback containment and exclude Zeno behavior during the control process. The effectiveness of the proposed event-triggered control method for fixed-time output feedback containment control of the second-order nonlinear MAS is verified by simulation examples. [ABSTRACT FROM AUTHOR]

The learning-based binocular 3D reconstruction method outperforms traditional vision algorithms in terms of precision and efficiency. However, in some cross-domain scenes, the precision of the well-trained network drastically decreases when handling samples in diverse contexts. This paper proposes an end-to-end shape-aware speckle matching network (SSMNet) that combines shape-mask information to achieve improved precision and completeness of disparity calculation in cross-domain applications. The cascade attention mechanism is inserted in the feature extraction stage to concentrate on valuable regions. The shape-aware module is designed to learn additional shape contour information, and multiscale features are integrated simultaneously to construct the cost-volume for the subsequent lightweight 3D aggregation. In addition, instance normalization is adopted to guarantee style migration, and a hybrid loss function is used to supervise the learning process. Furthermore, a high-precision binocular speckle dataset is built, including training and testing sets in different distributions. Extensive quantitative and qualitative experiments demonstrate that SSMNet enhances cross-domain capability and achieves state-of-the-art performance. Measurement precision evaluation illustrates that the proposed method can realize the desired highly precise 3D shape measurement in a real industrial scenario. [ABSTRACT FROM AUTHOR]

Knowledge graphs are large-scale semantic networks that considerably impact knowledge representation. Mining hidden knowledge from existing data, including triplet knowledge reasoning, is a primary objective of knowledge graphs. With the development of Neural Network (NN) and Deep Learning (DL), the interpretability of triplet knowledge reasoning gradually decreases; furthermore, what machines learn is not actual reasoning but digital reasoning shortcuts. To solve this problem, more background knowledge needs to be introduced into knowledge graphs: causal graphs can offer valuable causal logic knowledge for reasoning; temporal quadruples can provide essential temporal distribution details; and commonsense graphs can furnish pertinent commonsense understanding to support reasoning. In recent years, many scholars have incorporated additional background knowledge into knowledge graphs to construct more complex reasoning mechanisms. This paper reviews the basic concepts and definitions of knowledge reasoning and the reasoning methods used for knowledge graphs. Specifically, we dissect the reasoning methods into four categories: triplet reasoning, causal inference, temporal inference, and commonsense reasoning. Finally, we discuss the remaining challenges and research opportunities related to knowledge graph reasoning. [ABSTRACT FROM AUTHOR]

This paper focuses on the finite- and infinite-horizon optimal control problems of linear impulsive systems with periodic impulses under the quadratic performance index. Necessary and sufficient conditions for the optimal impulsive system are derived in terms of hybrid Riccati equations by utilizing the variational method and the collocation method combined with a time-varying Lyapunov function. Different from the existing model-based impulsive control schemes, three reinforcement learning (RL)-based algorithms are proposed to solve the optimal impulsive controller and hybrid controller for the impulsive system without the exact knowledge of the system dynamics. The asymptotical stability of the impulsive control system and the convergence of the RL-based algorithms are proved rigorously. Finally, a numerical simulation illustrates the effectiveness of the proposed control methods. [ABSTRACT FROM AUTHOR]

Medical image registration is a pivotal application within the field of medical imaging. It entails the fusion of commonalities among data of disparate modalities into a unified coordinate system, thereby achieving complementary imaging information. This process plays a crucial role in scenarios such as accurate disease diagnosis, surgical guidance, patient monitoring, and radiological therapy. Due to the distinct characteristics exhibited by changes in the same region over time or across different modalities, swiftly and accurately identifying corresponding relationships between pre-registered images remains a formidable challenge. This paper proposes the incorporation of an enhanced Artificial Rabbits Optimization (ARO) algorithm as an agent within the framework of reinforcement learning. The method, referred to as RL-mARO, is employed for medical image registration. By utilizing Normalized Mutual Information (NMI) as a reward and penalty feedback for the similarity metric, the agent continuously adjusts and alters the learning strategies within the population, thereby progressively converging towards the correct registration direction. The contribution of reinforcement learning to ARO was validated on the IEEE CEC2020 benchmark dataset. Simultaneously, registration experiments were conducted on the multi-modal brain dataset, Retrospective Image Registration Evaluation Project (RIRE), as well as the single-modal fundus dataset, Fundus Image Registration Dataset (FIRE). The results of both registration experiments demonstrate that the RL-mARO model exhibits elevated robustness and registration accuracy. [ABSTRACT FROM AUTHOR]

This paper addresses the sliding-mode surface-based adaptive optimal nonzero-sum games control problem for continuous-time nonlinear systems with input constraints. By constructing a value function associated with the sliding-mode surface, the original nonzero-sum games problem can be transformed into constructing multiple optimal control policies. Then, an adaptive dynamic programming method under identifier-critic networks is introduced to deal with the Hamilton–Jacobi equation, where the identifier networks are applied to approximate the unknown dynamics. A remarkable feature is that the critic updating laws are designed through experience replay and gradient descent methodologies, such that the persistence of excitation condition can be excluded. Based on the Lyapunov stability theory, all signals of the close-loop system are verified to be uniformly ultimately bounded. Finally, simulation results are given to illustrate the effectiveness of the proposed optimal nonzero-sum games scheme. [ABSTRACT FROM AUTHOR]

The six papers included in this special issue represent a selection of extended contributions presented at the 17th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2022 held in Salamanca, Spain, September 6th-8th, 2022, and organized by the BISITE group at the University of Salamanca. The International Conference on Hybrid Artificial Intelligence Systems (HAIS 2022) has become a unique, established, and broad interdisciplinary forum for researchers and practitioners who are involved in developing and applying symbolic and sub-symbolic techniques aimed at the construction of highly robust and reliable problem-solving techniques to present the most relevant achievements in this field. HAIS Series of Conferences provides an interesting opportunity to present and discuss the latest theoretical advances and real-world applications in this multidisciplinary research field. [ABSTRACT FROM AUTHOR]

The eight papers included in this special issue represent a selection of extended contributions presented at the 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022 held in Salamanca, Spain, September 6th-8th, 2022, and organized by the BISITE group at University of Salamanca. SOCO 2022 international conference represents a collection or set of computational techniques in machine learning, computer science and some engineering disciplines which investigate, simulate, and analyse very complex issues and phenomena. This special issue is aimed at practitioners, researchers, and postgraduate students who are engaged in developing and applying advanced intelligent systems principles to solve real-world problems in the mentioned fields. [ABSTRACT FROM AUTHOR]

Weakly supervised 3D object detection for autonomous driving primarily focuses on cars because of their distinct rectangle boundaries and abundant instances. However, detecting categories with ambiguous rectangle boundaries and fewer instances than cars, such as pedestrians and cyclists, remains challenging with limited research. Ambiguity in rectangle boundaries presents significant difficulties in generating accurate 3D pseudo labels, while the scarcity of instances often leads to convergence issues during detector training. Pedestrians and cyclists are dense inside the 3D bounding boxes but sparse at corners and boundaries. Density is a practical clue for locating and discriminating pedestrians and cyclists in point clouds. This paper proposes a density-based 3D pseudo-label generation module (DPL-3D), addressing the challenges of ambiguous rectangle boundaries. Ambiguity rectangle boundaries will lead to poor pseudo-label quality. Therefore, By leveraging the density information of 3D points, our DPL-3D improves the accuracy and localization quality of the generated pseudo labels. It effectively segments background points, improving the estimation of pseudo labels' location, dimension, and orientation. Few training samples always lead to local optima. Introducing multi-modal data in the detector network could enhance the constraints of objects' features, but 2D images and 3D point clouds have a resolution gap. A motivation for dealing with the resolution gap is that neighboring regions with similar colors and textures in 2D images may exhibit spatial proximity in 3D space. Therefore, a multi-modal network driven by superpixel segmentation is introduced. This network enables effective discrimination between objects in 2D images and 3D point clouds, bridging the resolution gap and leveraging complementary features from both modalities. Experimental results on the KITTI dataset demonstrate the effectiveness of the proposed methods in addressing the challenges associated with weakly-supervised 3D object detection, particularly for categories with ambiguous rectangle boundaries and few instances. [ABSTRACT FROM AUTHOR]

Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures yield good results. This paper proposes GEA, a novel approach for guided NAS. GEA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialization stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation. Subsequently, GEA continuously extracts knowledge about the search space without increased complexity by generating several off-springs from an existing architecture at each generation. Moreover, GEA forces exploitation of the most performant architectures by descendant generation while simultaneously driving exploration through parent mutation and favouring younger architectures to the detriment of older ones. Experimental results demonstrate the effectiveness of the proposed method, and extensive ablation studies evaluate the importance of different parameters. Results show that GEA achieves competitive results on all data sets of NAS-Bench-101, NAS-Bench-201 and TransNAS-Bench-101 benchmarks, as well as in the DARTS search space. [ABSTRACT FROM AUTHOR]