Skip to main content

Neural Processing Letters OnlineFirst articles


Periodic Stability on a Class of D-Operator-Based Neutral-Type Rayleigh Equations Accompanying Mixed Delays

In this paper, a class of D-operator-based neutral-type Rayleigh equations accompanying mixed delays is introduced, where the damping term is a continuous T-periodic function. Some new sufficient criteria are derived to guarantee the existence and …

verfasst von:
Weiping Fan


LMI-Based Synchronization Conditions to R-L Fractional Time-Varying Delayed Neural Networks with Parametric Uncertainty

The synchronization conditions to Riemann-Liouville fractional time-varying delayed neural networks with parametric uncertainty are investigated in this article. A novel Lyapunov-Krasovskii functional including double integral terms is proposed …

verfasst von:
Hongmei Zhang, Hai Zhang, Weiwei Zhang, Jinde Cao


Global Exponential Stability of Inertial Cohen–Grossberg Neural Networks with Time-Varying Delays via Feedback and Adaptive Control Schemes: Non-reduction Order Approach

In this article, the problem is dealt for the global exponential stability of delayed Cohen–Grossberg inertial neural networks (CGINNs) by constructing a new innovative Lyapunov functional instead of the traditional reduced-order method. The newly …

verfasst von:
Sunny Singh, Umesh Kumar, Subir Das, Jinde Cao


Neural Combinatorial Optimization with Explanation

Different from traditional operational research optimization algorithms, Deep Learning can solve combinatorial optimization problems in real time and has been widely used. However, these models based on pointer network have difficulty in obtaining …

verfasst von:
Zhaoyi Liu, Qianqian Duan


DDCNet-Multires: Effective Receptive Field Guided Multiresolution CNN for Dense Prediction

Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approaches to handle these challenges include hierarchical and …

verfasst von:
Ali Salehi, Madhusudhanan Balasubramanian


An Outlier-Robust Growing Local Model Network for Recursive System Identification

In this paper, we develop a self-growing variant of the local model network (LMN) for recursive dynamical system identification. The proposed model has the following features: growing online structure, fast recursive updating rules, better memory …

verfasst von:
Jéssyca A. Bessa, Guilherme A. Barreto, Ajalmar R. Rocha-Neto


Action-Aware Network with Upper and Lower Limit Loss for Weakly-Supervised Temporal Action Localization

Weakly-supervised temporal action localization aims to detect the temporal boundaries of action instances in untrimmed videos only by relying on video-level action labels. The main challenge of the research is to accurately segment the action from …

verfasst von:
Mingwen Bi, Jiaqi Li, Xinliang Liu, Qingchuan Zhang, Zhenghong Yang


Vector-Valued Hopfield Neural Networks and Distributed Synapse Based Convolutional and Linear Time-Variant Associative Memories

The Hopfield network is an example of an artificial neural network used to implement associative memories. A binary digit represents the neuron’s state of a traditional Hopfield neural network. Inspired by the human brain’s ability to cope …

verfasst von:
Rama Murthy Garimella, Marcos Eduardo Valle, Guilherme Vieira, Anil Rayala, Dileep Munugoti


Saliency Transfer Learning and Central-Cropping Network for Prostate Cancer Classification

Classifying the malignancy of prostate lesions from MRI images is crucial in diagnosing prostate cancer at the early stage. In clinical examination, radiologists usually focus on the most salient and distinctive regions to diagnose. However, in …

verfasst von:
Guokai Zhang, Mengpei Jia, Lin Gao, Jihao Luo, Aijun Zhang, Yongyong Chen, Peipei Shan, Binghui Zhao


A Step-by-Step Gradient Penalty with Similarity Calculation for Text Summary Generation

The summary generation model equipped with gradient penalty avoids overfitting and makes the model more stable. However, the traditional gradient penalty faces two issues: (i) calculating the gradient twice increases training time, and (ii) the …

verfasst von:
Shuai Zhao, Qing Li, Tengjiao He, Jinming Wen


Generate Usable Adversarial Examples via Simulating Additional Light Sources

Deep neural networks have been shown to be critically vulnerable under adversarial attacks. This has led to the proliferation of methods to generate different adversarial examples from different perspectives. The adversarial examples generated by …

verfasst von:
Chen Xi, Guo Wei, Zhang Fan, Du Jiayu


Application of Deep Learning Techniques in Diagnosis of Covid-19 (Coronavirus): A Systematic Review

Covid-19 is now one of the most incredibly intense and severe illnesses of the twentieth century. Covid-19 has already endangered the lives of millions of people worldwide due to its acute pulmonary effects. Image-based diagnostic techniques like …

verfasst von:
Yogesh H. Bhosale, K. Sridhar Patnaik


Multi-dimensional Taylor Network-Based Fault-Tolerant Control for Nonlinear Systems with Unmodeled Dynamics and Actuator Faults

This work investigates the problem of Multi-dimensional Taylor Network (MTN)-based fault-tolerant control (FTC) for single-input and single-output nonlinear systems in non-strict feedback form. A MTN-based FTC method is presented for nonlinear …

verfasst von:
Arun Bali, Uday Pratap Singh, Rahul Kumar


Counter Propagation Network Based Extreme Learning Machine

The extreme learning machine (ELM), a new learning algorithm for single hidden layer feedforward neural networks (SLFN), has drawn interest of a large number of researchers, especially due to its training speed and good generalization performances …

verfasst von:
Gökhan Kayhan, İsmail İşeri


Real Time Air-Written Mathematical Expression Recognition for Children’s Enhanced Learning

Air-writing is the process where, without the assistance of any handheld device, users use finger or hand gestures to write a character or words in free space. Due to its simple writing style, it has a great advantage over conventional …

verfasst von:
Shobhan Kumar, Munesh Chandra Trivedi, Arun Chauhan


ROCM: A Rolling Iteration Clustering Model Via Extracting Data Features

The allocation of boundary points and low-density clusters has become an essential part of clustering research. Most of the recent improved methods that focused on identifing allocation of points have not addressed the issue of specific data point …

verfasst von:
Linliang Guo, Limin Wang, Xuming Han, Lin Yue, Yihang Zhang, Minghan Gao


Modified Newton Integration Neural Algorithm for Solving Time-Varying Yang-Baxter-Like Matrix Equation

This paper intends to solve the time-varying Yang-Baxter-like matrix equation (TVYBLME), which is frequently employed in the fields of scientific computing and engineering applications. Due to its critical and promising role, several methods have …

verfasst von:
Haoen Huang, Zifan Huang, Chaomin Wu, Chengze Jiang, Dongyang Fu, Cong Lin


Adaptive Decentralized Tracking Control for a Class of Large-Scale Nonlinear Systems with Dynamic Uncertainties Using Multi-dimensional Taylor Network Approach

For the large-scale nonlinear systems subject to dynamic uncertainties, an adaptive multi-dimensional Taylor network (MTN)-based decentralized control strategy is proposed, which can effectively solve output tracking control problem of the …

verfasst von:
Zheng-Duo Shan, Wen-Jing He, Yu-Qun Han, Shan-Liang Zhu


Fixed-Time Anti-synchronization and Preassigned-Time Synchronization of Discontinuous Fuzzy Inertial Neural Networks with Bounded Distributed Time-Varying Delays

This paper is dedicated to fixed-time anti-synchronization (FXTAS) and preassigned-time synchronization (PATS) of discontinuous fuzzy inertial neural networks with mixed time-varying delays. Different from the traditional continuous neural network …

verfasst von:
Yang Liu, Guodong Zhang, Junhao Hu

03.09.2022 | Correction

Correction to: Region Centric Minutiae Propagation Measure Orient Forgery Detection with Finger Print Analysis in Health Care Systems

The article “Region Centric Minutiae Propagation Measure Orient Forgery Detection with Finger Print Analysis in Health Care Systems”, written by M. Baskar, R. Renuka Devi, J. Ramkumar, P. Kalyanasundaram, M. Suchithra and B. Amutha, was originally …

verfasst von:
M. Baskar, R. Renuka Devi, J. Ramkumar, P. Kalyanasundaram, M. Suchithra, B. Amutha