查看更多>>摘要：This paper aims at solving a stochastic two-player zero-sum Nash game problem studied in Singh and Lisser (2019). The main contribution of our paper is that we model this game problem as a dynamical neural network (DNN for short). In this paper, we show that the saddle point of this game problem is the equilibrium point of the DNN model, and we study the globally asymptotically stable of the DNN model. In our numerical experiments, we present the time-continuous feature of the DNN model and compare it with the state-of-the-art convex solvers, i.e., Splitting conic solver (SCS for short) and Cvxopt. Our numerical results show that our DNN method has two advantages in dealing with this game problem. Firstly, the DNN model can converge to a better optimal point. Secondly, the DNN method can solve all problems, even when the problem size is large. (C) 2022 Elsevier Ltd. All rights reserved.
Bekhouche, S. E.Kajo, I.Ruichek, Y.Dornaika, F....
10页
查看更多>>摘要：Eye blink detection is a challenging problem that many researchers are working on because it has the potential to solve many facial analysis tasks, such as face anti-spoofing, driver drowsiness detection, and some health disorders. There have been few attempts to detect blinking in the wild scenario, while most of the work has been done under controlled conditions. Moreover, current learning approaches are designed to process sequences that contain only a single blink ignoring the case of the presence of multiple eye blinks. In this work, we propose a fast framework for eye blink detection and eye blink verification that can effectively extract multiple blinks from image sequences considering several challenges such as lighting changes, variety of poses, and change in appearance. The proposed framework employs fast landmarks detector to extract multiple facial key points including the ones that identify the eye regions. Then, an SVD-based method is proposed to extract the potential eye blinks in a moving time window that is updated with new images every second. Finally, the detected blink candidates are verified using a 2D Pyramidal Bottleneck Block Network (PBBN). We also propose an alternative approach that uses a sequence of frames instead of an image as input and employs a continuous 3D PBBN that follows most of the state-of-the-art approaches schemes. Experimental results show the better performance of the proposed approach compared to the state-of-the-art approaches.(c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
查看更多>>摘要：Square matrices appear in many machine learning problems and models. Optimization over a large square matrix is expensive in memory and in time. Therefore an economic approximation is needed. Conventional approximation approaches factorize the square matrix into a number matrices of much lower ranks. However, the low-rank constraint is a performance bottleneck if the approximated matrix is intrinsically high-rank or close to full rank. In this paper, we propose to approximate a large square matrix with a product of sparse full-rank matrices. In the approximation, our method needs only N(log N)(2) non-zero numbers for an N x N full matrix. Our new method is especially useful for scalable neural attention modeling. Different from the conventional scaled dot-product attention methods, we train neural networks to map input data to the non-zero entries of the factorizing matrices. The sparse factorization method is tested for various square matrices, and the experimental results demonstrate that our method gives a better approximation when the approximated matrix is sparse and high rank. As an attention module, our new method defeats Transformer and its several variants for long sequences in synthetic data sets and in the Long Range Arena benchmarks. Our code is publicly available(2). (C) 2022 The Author(s) .Published by Elsevier Ltd.
查看更多>>摘要：This paper addresses a new interpretation of the traditional optimization method in reinforcement learning (RL) as optimization problems using reverse Kullback-Leibler (KL) divergence, and derives a new optimization method using forward KL divergence, instead of reverse KL divergence in the optimization problems. Although RL originally aims to maximize return indirectly through optimization of policy, the recent work by Levine has proposed a different derivation process with explicit consideration of optimality as stochastic variable. This paper follows this concept and formulates the traditional learning laws for both value function and policy as the optimization problems with reverse KL divergence including optimality. Focusing on the asymmetry of KL divergence, the new optimization problems with forward KL divergence are derived. Remarkably, such new optimization problems can be regarded as optimistic RL. That optimism is intuitively specified by a hyperparameter converted from an uncertainty parameter. In addition, it can be enhanced when it is integrated with prioritized experience replay and eligibility traces, both of which accelerate learning. The effects of this expected optimism was investigated through learning tendencies on numerical simulations using Pybullet. As a result, moderate optimism accelerated learning and yielded higher rewards. In a realistic robotic simulation, the proposed method with the moderate optimism outperformed one of the state-of-the-art RL method. (C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Blood pressure (BP) is known as an indicator of human health status, and regular measurement is helpful for early detection of cardiovascular diseases. Traditional techniques for measuring BP are either invasive or cuff-based and thus are not suitable for continuous measurement. Aiming at the deficiencies in existing studies, a novel cuffless BP estimation framework of Receptive Field Parallel Attention Shrinkage Network (RFPASN) and BP range constraint is proposed. Firstly, RFPASN uses the multi-scale large receptive field convolution module to capture the long-term dynamics in the photoplethysmography (PPG) signal without using long short-term memory (LSTM). On this basis, the features acquired by the parallel mixed domain attention module are used as thresholds, and the soft threshold function is used to screen the input features to enhance the discriminability and robustness of features, which can significantly improve the prediction accuracy of diastolic blood pressure (DBP) and systolic blood pressure (SBP). Finally, in order to prevent large fluctuations in the prediction results of RFPASN, RFPASN based on BP range constraint is proposed to make the prediction results of RFPASN more accurate and reasonable. The performance of the proposed method is demonstrated on a publically available MIMIC-II database. The database contains normal, hypertensive and hypotensive people. We have achieved MAE of 1.63/1.59 (DBP) and 2.26/2.15 (SBP) mmHg for BP on total population of 1562 subjects. A comparative study shows that the proposed algorithm is more promising than the state-of-the-art.(C) 2022 Published by Elsevier Ltd.
查看更多>>摘要：Wrong-labeling problem and long-tail relations severely affect the performance of distantly supervised relation extraction task. Many studies mitigate the effect of wrong-labeling through selective attention mechanism and handle long-tail relations by introducing relation hierarchies to share knowledge. However, almost all existing studies ignore the fact that, in a sentence, the appearance order of two entities contributes to the understanding of its semantics. Furthermore, they only utilize each relation level of relation hierarchies separately, but do not exploit the heuristic effect between relation levels, i.e., higher-level relations can give useful information to the lower ones. Based on the above, in this paper, we design a novel Recursive Hierarchy-Interactive Attention network (RHIA) to further handle long-tail relations, which models the heuristic effect between relation levels. From the top down, it passes relation-related information layer by layer, which is the most significant difference from existing models, and generates relation-augmented sentence representations for each relation level in a recursive structure. Besides, we introduce a newfangled training objective, called Entity-Order Perception (EOP), to make the sentence encoder retain more entity appearance information. Substantial experiments on the popular New York Times (NYT) dataset are conducted. Compared to prior baselines, our RHIA-EOP achieves state-of-the-art performance in terms of precision-recall (P-R) curves, AUC, Top-N precision and other evaluation metrics. Insightful analysis also demonstrates the necessity and effectiveness of each component of RHIA-EOP. (C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and achieved remarkable progress. However, most of the existing CNN-based SISR networks with a single-stream structure fail to make full use of the multi-scale features of low resolution (LR) image. While those multi-scale SR models often integrate the information with different receptive fields by means of linear fusion, which leads to the redundant feature extraction and hinders the reconstruction performance of the network. To address both issues, in this paper, we propose a non-linear perceptual multi-scale network (NLPMSNet) to fuse the multi-scale image information in a non-linear manner. Specifically, a novel non-linear perceptual multi-scale module (NLPMSM) is developed to learn more discriminative multi-scale feature correlation by using high-order channel attention mechanism, so as to adaptively extract image features at different scales. Besides, we present a multi-cascade residual nested group (MC-RNG) structure, which uses a global multi-cascade mechanism to organize multiple local residual nested groups (LRNG) to capture sufficient non local hierarchical context information for reconstructing high-frequency details. LRNG uses a local residual nesting mechanism to stack NLPMSMs, which aims to form a more effective residual learning mechanism and obtain more representative local features. Experimental results show that, compared with the state-of-the-art SISR methods, the proposed NLPMSNet performs well in both quantitative metrics and visual quality with a small number of parameters. (C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：In this paper, an event-triggered integral reinforcement learning (IRL) algorithm is developed for the nonzero-sum game problem with asymmetric input saturation. First, for each player, a novel non quadratic value function with a discount factor is designed, and the coupled Hamilton-Jacobi equation that does not require a complete knowledge of the game is derived by using the idea of IRL. Second, the execution of each player is based on the event-triggered mechanism. In the implementation, an adaptive dynamic programming based learning scheme using a single critic neural network (NN) is developed. Experience replay technique is introduced into the classical gradient descent method to tune the weights of the critic NN. The stability of the system and the elimination of Zeno behavior are proved. Finally, simulation experiments verify the effectiveness of the event-triggered IRL algorithm. (C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Attributed graph clustering is challenging as it needs to effectively combine both graph structure and node feature information to accomplish node clustering. Recent studies mostly adopt graph neural networks to learn node embeddings, then apply traditional clustering methods to obtain clusters. However, their node embeddings are not specifically designed for clustering. Moreover, most of their loss functions only rely on either structure or feature information, making both kinds of information not fully retained in node embeddings. In this paper, we propose a multi-task embedding learning method (MTEL) for attributed graph clustering, which constructs two prediction tasks in terms of structure and feature based adjacency matrices respectively. To make the node embeddings helpful for the downstream clustering, in each task, we predict the minimum hop number between each pair of nodes in the adjacency matrix, so that the correlation degrees among nodes can be encoded into node embeddings. To improve the performance of the prediction task, we regularize the model parameters in these two tasks via l(2,1) norm, through which the model parameters can be jointly learned. Experiments on real attributed graphs show that MTEL is superior for attributed graph clustering over state-of-the-art methods. (C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：We present a novel artificial cognitive mapping system using generative deep neural networks, called variational autoencoder/generative adversarial network (VAE/GAN), which can map input images to latent vectors and generate temporal sequences internally. The results show that the distance of the predicted image is reflected in the distance of the corresponding latent vector after training. This indicates that the latent space is self-organized to reflect the proximity structure of the dataset and may provide a mechanism through which many aspects of cognition are spatially represented. The present study allows the network to internally generate temporal sequences that are analogous to the hippocampal replay/pre-play ability, where VAE produces only near-accurate replays of past experiences, but by introducing GANs, the generated sequences are coupled with instability and novelty. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
NSTL
Elsevier