Jing Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jing Hou has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Dongfang Hou
Engineering & Technology Department, University of Wisconsin Stout, Menomonie, WI 54751, USA
1 shared publication - Mohammad Arifuzzaman
Department of Mathematics, Statistics & Computer Science, University of Wisconsin-Stout, Menomonie, WI 54751, USA
1 shared publication - Tao Jiang
Crop Transformation Center, Department of Horticultural Sciences, Institute of Food and Agricultural Sciences (IFAS), University of Florida, Gainesville, USA
1 shared publication - Tran Duc Le
Department of Mathematics, Statistics & Computer Science, University of Wisconsin-Stout, Menomonie, WI 54751, USA
1 shared publication - Yida Bao
Department of Mathematics, Statistics & Computer Science, University of Wisconsin-Stout, Menomonie, WI 54751, USA
1 shared publication - Yuan Xing
Department of Engineering Technology, University of Wisconsin-Stout, Menomonie, WI 54751, USA
1 shared publication
Latest Publications
- Open Access
- 28 February 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (3) , 71
A Convergent Method for Energy Optimization in Modern Hopfield Networks
Modern Hopfield networks are energy-based associative memory models whose performance critically depends on the structure and optimization of their energy functions. While recent formulations substantially improve storage capacity, the resulting non-convex energy landscapes are often optimized using heuristic update rules that can be sensitive to initialization and may not provide monotonic energy descent or rigorous convergence guarantees. In this work, we propose a new energy formulation for modern Hopfield networks together with a principled iterative optimization scheme. The proposed energy admits a natural decomposition that allows optimization via the concave–convex procedure (CCCP), yielding well-defined network dynamics with guaranteed energy descent beyond classical Hopfield updates. We establish fundamental theoretical properties of the proposed framework, including non-negativity, boundedness, and monotonic decrease in the energy along iterations. In particular, we prove that the induced dynamics converge to a stationary point of the energy function, providing explicit convergence guarantees for the resulting Hopfield-type model. We further evaluate the proposed approach on synthetic classification tasks and compare its optimization behavior with that of the original Hopfield network and several standard machine learning baselines. Experimental results demonstrate improved stability, convergence behavior, and competitive classification performance. We also validate the approach on real-world benchmark datasets to demonstrate utility beyond controlled experiments. Overall, this work provides a theoretically grounded energy-based optimization framework for modern Hopfield networks, clarifying the role of principled optimization in achieving stable and convergent associative memory dynamics.
- 28 February 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (3) , 71
Open AccessA Convergent Method for Energy Optimization in Modern Hopfield Networks
Modern Hopfield networks are energy-based associative memory models whose performance critically depends on the structure and optimization of their energy functions. While recent formulations substantially improve storage capacity, the resulting non-convex energy landscapes are often optimized using heuristic update rules that can be sensitive to initialization and may not provide monotonic energy descent or rigorous convergence guarantees. In this work, we propose a new energy formulation for modern Hopfield networks together with a principled iterative optimization scheme. The proposed energy admits a natural decomposition that allows optimization via the concave–convex procedure (CCCP), yielding well-defined network dynamics with guaranteed energy descent beyond classical Hopfield updates. We establish fundamental theoretical properties of the proposed framework, including non-negativity, boundedness, and monotonic decrease in the energy along iterations. In particular, we prove that the induced dynamics converge to a stationary point of the energy function, providing explicit convergence guarantees for the resulting Hopfield-type model. We further evaluate the proposed approach on synthetic classification tasks and compare its optimization behavior with that of the original Hopfield network and several standard machine learning baselines. Experimental results demonstrate improved stability, convergence behavior, and competitive classification performance. We also validate the approach on real-world benchmark datasets to demonstrate utility beyond controlled experiments. Overall, this work provides a theoretically grounded energy-based optimization framework for modern Hopfield networks, clarifying the role of principled optimization in achieving stable and convergent associative memory dynamics.