Article
Mathematics, Interdisciplinary Applications
Fen Wang, Yuanlong Chen
Summary: This paper investigates the mean square exponential stability of stochastic memristor-based neural networks with leakage delay under the framework of Filippov solutions. Criteria for stability are established using Lyapunov-Krasovskii functional, Ito's differential formula, Schur complement lemma, and linear matrix inequality technique. The proposed criteria do not require activation function's boundedness, differentiability, and monotonicity, and are efficiently checked using MATLAB toolbox. Three numerical examples are provided to illustrate the effectiveness of the results.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Computer Science, Artificial Intelligence
Aidi Liu, Hui Zhao, Qingjie Wang, Sijie Niu, Xizhan Gao, Chuan Chen, Lixiang Li
Summary: In this paper, two novel and general predefined-time stability lemmas are proposed and applied to the predefined-time synchronization problem of memristive complex-valued bidirectional associative memory neural networks (MCVBAMNNs). The effectiveness of the results is verified through numerical simulation. A secure communication scheme based on the predefined-time synchronization of MCVBAMNNs is also proposed.
Article
Computer Science, Artificial Intelligence
Fanhong Zhang, Chen Fei, Weiyin Fei
Summary: In this paper, the pth exponential stability and quasi-surely exponential stability of stochastic Hopfield neural networks driven by G-Brownian motion are investigated. Several lemmas related to the Halanay inequality and the Burkholder-Davis-Gundy inequality are given under a sublinear expectation framework. The main originality lies in considering the Knightian uncertainty of the theory model. Numerical examples are presented to illustrate the new theory.
Article
Automation & Control Systems
Zhiguang Liu, Quanxin Zhu
Summary: This article discusses a class of nonlinear hybrid stochastic differential delay equations with Poisson jump and different structures. The jump makes the analysis more complex due to the discontinuity of its sample paths compared to Brownian motion. Moreover, the coefficients meet a novel nonlinear growth condition and different structures in different switch modes. By using M-matrices and Lyapunov functions, the article proves the existence-uniqueness, asymptotic boundedness, and exponential stability of the solution. Finally, two examples are provided to demonstrate the usefulness of the theory.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Automation & Control Systems
Liping Yin, Yawei Han, Gongfei Song, Guoying Miao, Tao Li
Summary: This paper studies the stabilization of a complex dynamic model with nonlinearities, uncertainty, and Levy noises. It proposes a new algorithm to determine the upper bound for the sample interval that ensures the exponential stability of the discrete system. Firstly, an integral sliding surface is designed using Lyapunov theory and generalized Ito formula to prove the exponential stability in mean square sense. Secondly, the continuous-time controller is discretized and the squared difference of states is analyzed. The largest sampling interval that stabilizes the Levy process driven stochastic system is obtained.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Mathematics, Interdisciplinary Applications
Jianglian Xiang, Junwu Ren, Manchun Tan
Summary: This paper discusses the asymptotical synchronization and the input-to-state exponential stability of multi-layer networks based on memristors with delays under coupling disturbance and stochastic noise. Differential inclusion and Laplace transform methods are used to address the nonlinear coupling function and discontinuous activation. New sufficient conditions based on Lyapunov-Krasovskii functional, inequality technique, and linear matrix inequality are derived to ensure the stability of the considered model. Two examples and simulations are provided to illustrate the validity and correctness of the conclusions.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Mathematics, Applied
Tomas Caraballo, Lassaad Mchiri, Belfeki Mohsen, Mohamed Rhaima
Summary: This paper focuses on the pth moment exponential stability of neutral stochastic pantograph differential equations with Markovian switching (NSPDEwMS). By utilizing the Lyapunov method, sufficient conditions for the pth moment exponential stability of NSPDEwMS are developed. Two examples are analyzed to demonstrate the significance of the main results.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2021)
Article
Mathematics, Applied
Yutian Zhang, Guici Chen, Qi Luo
Summary: This paper investigates the pth moment exponential stability for a class of impulsive delayed Hopfield neural networks and provides concise algebraic criteria through a new method. The results show that neither a complicated Lyapunov function nor the differentiability of the delay function is required for the discussion.
JOURNAL OF INEQUALITIES AND APPLICATIONS
(2021)
Article
Automation & Control Systems
Yang Liu, Junyan Xu, Jianquan Lu, Weihua Gui
Summary: This paper investigates the pth moment exponential stability of impulsive stochastic time-delay systems (STDS) with random impulsive delay. A new concept of average random delay in impulses is introduced to study the pth moment exponential stability of STDS, providing a novel perspective on the study of stochastic delay in impulses. The destabilizing and stabilizing effects of delayed impulses are examined, and it is revealed that random delay in impulses significantly impacts the stability of the system. The results allow for delays in both continuous dynamics and impulsive dynamics to exceed the length of the impulsive interval, making them more general than previous findings. Numerical simulations are presented to illustrate the proposed results.
Article
Mathematics, Interdisciplinary Applications
Jose J. Oliveira
Summary: This paper provides sufficient conditions for the global asymptotic stability of a general n-dimensional nonautonomous and nonlinear differential equation with infinite delay. The main stability criterion depends on the delay size on the linear part and the dominance of linear terms over nonlinear terms. The obtained theoretical stability results are applied to answer open problems and generalize a bidirectional associative memory neural network model with delays. A numerical example is given to illustrate the novelty of the results.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Computer Science, Information Systems
R. Sriraman, Prasanalakshmi Balaji, R. Veerasivaji
Summary: This study explores new theoretical results for the global exponential stability of bidirectional associative memory delayed neural networks in the Clifford domain. By considering time-varying delays, a general class of Clifford-valued bidirectional associative memory neural networks is formulated, which encompasses real-, complex-, and quaternion-valued neural network models as special cases. New sufficient conditions are established to guarantee the existence, uniqueness, and global exponential stability of equilibrium points for the considered networks by constructing a new Lyapunov functional and applying homeomorphism theory. The obtained theoretical results are validated through a numerical example and simulation results, and remain valid even when the considered neural networks degenerate into real-, complex-, and quaternion-valued networks.
Article
Automation & Control Systems
Ning Yang, Dongyan Chen, Jun Hu
Summary: This study focuses on the boundedness and stability of a nonlinear hybrid stochastic differential delay equation disturbed by Levy noise. Different parameters and structures under different modes are considered, and a novel Lyapunov function is constructed to handle these differences. The existence of a global solution is proved, and the M-matrix technique is applied to establish theorems regarding the asymptotic boundedness and exponential stability of moments. Numerical examples and simulations are provided to demonstrate the usefulness of the findings.
IET CONTROL THEORY AND APPLICATIONS
(2023)
Article
Mathematics
Qingchao Meng, Huamin Wang
Summary: In this paper, a novel memristor-based non-delay Hopfield neural network with impulsive effects is designed in a quaternion field. Some special inequalities, differential inclusion, Hamilton rules and impulsive system theories are utilized in this manuscript to investigate potential solutions and obtain some sufficient criteria. In addition, through choosing proper mu(t) and impulsive points, the global mu-stability of the solution is discussed and some sufficient criteria are presented by special technologies. Then, from the obtained sufficient criteria of global mu-stability, other stability criteria including exponential stability and power stability can be easily derived. Finally, one numerical example is given to illustrate the feasibility and validity of the derived conclusions.
Article
Computer Science, Artificial Intelligence
Liangchen Li, Rui Xu, Qintao Gan, Jiazhe Lin
Summary: This paper investigates a novel neural network model utilizing memristor-resistor bridge synapses for continuously adjustable connection weights. The study establishes a model that retains the memory characteristic of memristors and explores the state synchronization of the model under the influence of Levy noise. By applying controllers to each synapse, complete synchronization of the drive and response networks is achieved. Numerical examples demonstrate the feasibility of the theoretical results.
Article
Computer Science, Artificial Intelligence
Chi Zhao, Yinfang Song, Yurong Liu, Fawaz E. Alsaadi
Summary: This article investigates the pth moment synchronization problem for stochastic impulsive neural networks (SINNs) with time-varying coefficients and unbounded delays. A new impulse generation rule and impulsive differential inequalities are proposed to handle the complexities of the network. The synchronization of SINNs is analyzed in detail, and both pth moment exponential synchronization and asymptotical synchronization are achieved through appropriate feedback controllers.
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.