Haoen Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haoen Huang has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Zhigang Zeng
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, CHINA
14 shared publications - Dongyang Fu
Guangdong Ocean University
11 shared publications - Xiuchun Xiao
School of Electronic and Information Engineering, Guangdong Ocean University, Zhanjiang 524088, China
8 shared publications - Long Jin
Lanzhou University
6 shared publications - Depeng Li
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, CHINA
4 shared publications - Guancheng Wang
College of Electronic and Information Engineering, Guangdong Ocean University, Zhanjiang 524088, China
4 shared publications
Latest Publications
- 2 November 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Integral-chain gradient neurodynamics: Error-envelope contraction for time-varying linear equation solvers
- 2 November 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Integral-chain gradient neurodynamics: Error-envelope contraction for time-varying linear equation solvers
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37  (11) , 5864-5876
Sliding Integral Neural Network Driven Robust Solution for Time-Varying Quadratic Programming
Time-varying quadratic programming (TVQP) requires efficient, accurate, and robust online solvers. Existing discrete-time (DT) recurrent neural networks (RNNs), however, often face a tradeoff between solution precision and noise immunity. To address this issue, a sliding integral neural network (SINN) is proposed. In particular, the interior-point (IP) method is extended to a dynamic IP (DIP) formulation with a time-varying barrier coefficient, and TVQP is reformulated as a DT error-feedback system for closed-loop design. A sliding integral control law with forward harmonic vectors is then developed to compensate for iterative differential residuals. Theoretical analyses show that the SINN achieves $\boldsymbol {O}(\tau ^{4})$ steady-state accuracy, where $\tau $ denotes the sampling interval, and suppresses structured disturbances with sublinear/linear growth. Numerical and robotic arm motion-planning simulations demonstrate its high precision and robustness.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37  (11) , 5864-5876
Sliding Integral Neural Network Driven Robust Solution for Time-Varying Quadratic Programming
Time-varying quadratic programming (TVQP) requires efficient, accurate, and robust online solvers. Existing discrete-time (DT) recurrent neural networks (RNNs), however, often face a tradeoff between solution precision and noise immunity. To address this issue, a sliding integral neural network (SINN) is proposed. In particular, the interior-point (IP) method is extended to a dynamic IP (DIP) formulation with a time-varying barrier coefficient, and TVQP is reformulated as a DT error-feedback system for closed-loop design. A sliding integral control law with forward harmonic vectors is then developed to compensate for iterative differential residuals. Theoretical analyses show that the SINN achieves $\boldsymbol {O}(\tau ^{4})$ steady-state accuracy, where $\tau $ denotes the sampling interval, and suppresses structured disturbances with sublinear/linear growth. Numerical and robotic arm motion-planning simulations demonstrate its high precision and robustness.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37  (11) , 6129-6139
An Accelerated Augmented Gradient Neural Network for Constrained Time-Varying Nonlinear Optimization
The constrained time-varying nonlinear optimization (CTVNO) problems with the linear equality and inequality constraints have attracted increasing attention in recent years. Although some models have been developed to address these problems, they still suffer from two critical limitations: complex model architecture and slow transient response. These issues restrict their practical application in engineering. To overcome these drawbacks, an accelerated augmented gradient neural network (AAGNN) is proposed. By integrating the error function with energy function gradients, the AAGNN efficiently exploits the essential information of the original problem, thereby reducing the complexity and accelerating convergence. The theoretical analysis demonstrates that the proposed AAGNN excels in achieving high-precision solutions. This stems from its ability to rapidly eliminate large errors through the exponential convergence. Comparative numerical experiments across four benchmarks demonstrate that the AAGNN consistently achieves a lower residual error and faster convergence than existing models. Furthermore, application tests through robotic manipulator trajectory tracking control and portfolio selection of marketed securities confirm the model’s superior practical applicability in real-world scenarios.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37  (11) , 6129-6139
An Accelerated Augmented Gradient Neural Network for Constrained Time-Varying Nonlinear Optimization
The constrained time-varying nonlinear optimization (CTVNO) problems with the linear equality and inequality constraints have attracted increasing attention in recent years. Although some models have been developed to address these problems, they still suffer from two critical limitations: complex model architecture and slow transient response. These issues restrict their practical application in engineering. To overcome these drawbacks, an accelerated augmented gradient neural network (AAGNN) is proposed. By integrating the error function with energy function gradients, the AAGNN efficiently exploits the essential information of the original problem, thereby reducing the complexity and accelerating convergence. The theoretical analysis demonstrates that the proposed AAGNN excels in achieving high-precision solutions. This stems from its ability to rapidly eliminate large errors through the exponential convergence. Comparative numerical experiments across four benchmarks demonstrate that the AAGNN consistently achieves a lower residual error and faster convergence than existing models. Furthermore, application tests through robotic manipulator trajectory tracking control and portfolio selection of marketed securities confirm the model’s superior practical applicability in real-world scenarios.
- 17 July 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114  (14) , 917
An Attention-Subspace-Assisted Collaborative Neurodynamic Optimization Approach for Time-Varying Constrained Nonconvex Optimization
- 17 July 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114  (14) , 917
An Attention-Subspace-Assisted Collaborative Neurodynamic Optimization Approach for Time-Varying Constrained Nonconvex Optimization
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP  (10) , 1-13
A Collaborative Neural Network With Adaptive Gradient Dynamics for Nonconvex Optimization
In this article, a collaborative neural network (CONN) with adaptive gradient dynamics is presented for addressing nonconvex optimization problems. Existing neural dynamics models often suffer from either prohibitive computational costs or unsatisfactory performance, which limits their practical effectiveness. To overcome this, an adaptive gradient neural dynamics (AGND) model is developed for local optimization in nonconvex problems, achieving reduced computational complexity and superior performance. Subsequently, a CONN is proposed that combines multiple AGND models for scattered searches with a metaheuristic rule that reinitializes neuronal states upon local convergence. Theoretical analysis establishes that the AGND model ensures local optimality, and further demonstrates the global convergence of the proposed CONN. Extensive experiments on numerous classical time-invariant nonconvex optimization benchmark problems illustrate the effectiveness and stability of the CONN. Moreover, the proposed method consistently achieves strong performance across diverse application problems, including both time-varying and time-invariant scenarios, such as robotic manipulator trajectory tracking, portfolio selection, and pressure vessel design.
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP  (10) , 1-13
A Collaborative Neural Network With Adaptive Gradient Dynamics for Nonconvex Optimization
In this article, a collaborative neural network (CONN) with adaptive gradient dynamics is presented for addressing nonconvex optimization problems. Existing neural dynamics models often suffer from either prohibitive computational costs or unsatisfactory performance, which limits their practical effectiveness. To overcome this, an adaptive gradient neural dynamics (AGND) model is developed for local optimization in nonconvex problems, achieving reduced computational complexity and superior performance. Subsequently, a CONN is proposed that combines multiple AGND models for scattered searches with a metaheuristic rule that reinitializes neuronal states upon local convergence. Theoretical analysis establishes that the AGND model ensures local optimality, and further demonstrates the global convergence of the proposed CONN. Extensive experiments on numerous classical time-invariant nonconvex optimization benchmark problems illustrate the effectiveness and stability of the CONN. Moreover, the proposed method consistently achieves strong performance across diverse application problems, including both time-varying and time-invariant scenarios, such as robotic manipulator trajectory tracking, portfolio selection, and pressure vessel design.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56  (6) , 3165-3176
An Integral-Enhanced Adaptive Gradient Neural Network for k WTA and Multirobot Coordination
Existing computational methods for the $k$ -winners-take-all ( $k$ WTA) operations often suffer from limitations in eliminating lagging errors, high computational complexity, and weak robustness. To deal with these challenges, we propose an integral-enhanced adaptive gradient neural network (IAGNN) for $k$ WTA. We demonstrate that the IAGNN integrates an adaptive coefficient to eliminate lagging errors while retaining an $O(n^{2})$ computational complexity. We proved the Lyapunov stability and robustness of the IAGNN. We provide a numerical simulation, and the results demonstrate the stability and robustness of the IAGNN. Furthermore, we implement the IAGNN in a multirobot tracking system for competitive allocation coordination, and the results demonstrate the operational feasibility and noise resistance of the IAGNN.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56  (6) , 3165-3176
An Integral-Enhanced Adaptive Gradient Neural Network for k WTA and Multirobot Coordination
Existing computational methods for the $k$ -winners-take-all ( $k$ WTA) operations often suffer from limitations in eliminating lagging errors, high computational complexity, and weak robustness. To deal with these challenges, we propose an integral-enhanced adaptive gradient neural network (IAGNN) for $k$ WTA. We demonstrate that the IAGNN integrates an adaptive coefficient to eliminate lagging errors while retaining an $O(n^{2})$ computational complexity. We proved the Lyapunov stability and robustness of the IAGNN. We provide a numerical simulation, and the results demonstrate the stability and robustness of the IAGNN. Furthermore, we implement the IAGNN in a multirobot tracking system for competitive allocation coordination, and the results demonstrate the operational feasibility and noise resistance of the IAGNN.
- 9 January 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114  (2) , 91
Memristor-based nonlinear neural dynamics with a step-variable edge learning scheme for device non-idealities
- 9 January 2026
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 114  (2) , 91
Memristor-based nonlinear neural dynamics with a step-variable edge learning scheme for device non-idealities
- 8 January 2026
- Published by Elsevier in Neural Networks
- Vol. 197, 108547
A memristive fuzzy neural network with applications to classification task: A programmable circuit system
- 8 January 2026
- Published by Elsevier in Neural Networks
- Vol. 197, 108547
A memristive fuzzy neural network with applications to classification task: A programmable circuit system
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 16673-16687
Reconstruction-Free Vision-Based Control via Differentiable Long-Horizon Influence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 16673-16687
Reconstruction-Free Vision-Based Control via Differentiable Long-Horizon Influence