Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2602.06420

Integrating AI and Quantum-Inspired Techniques for Efficient Enzyme Fermentation Optimization

Ying-Wei Tseng, Yu-Ting Kao, Yeong-Jar Chang, Jia-Han Ou, Wen-Zhi Zhang, Jin-Jia Wang, Yung-Hsiang Lin

quant-phSubmitted Feb 6, 2026• Announced Feb 9, 2026• Revised Feb 9, 2026 (v2)
v1 · Feb 6, 2026v2 · Feb 9, 2026
arXivHTMLPDF

Abstract

This paper introduces a new method that combines Artificial Intelligence (AI) and quantum-inspired techniques to improve the efficiency of multi-variable optimization experiments. By using advanced software simulations, this approach significantly reduces the time and cost compared to traditional physical experiments. The research focuses on enzyme fermentation, demonstrating that this method can achieve better results with fewer experiments. The findings highlight the potential of this approach to more effectively identify optimal formulations, leading to advancements in enzyme fermentation and other fields that require complex optimization. Initially, the Active Ingredients (AIN) could not be improved even after 600 experiments. However, by adopting the method outlined in this paper, we were able to identify a better formula in just 405 experiments. This resulted in an increase of AIN from 8481 to 10068, representing an improvement of 18.7%.

Comments
12 pages, 6 figures

Related papers

Quantum-Inspired AI Models for Optimizing Semiconductor Device Performance

The rapid advance in semiconductor technology requires novelty in approach to improve device performance and efficiency.This paper discusses the use of quantum-inspired AI models as a state-of-the-art solution for the optimization of semiconductor devices.We create and train these AI models with the help of real datasets to make accurate predictions and improvements in important performance parameters of different semiconductor components.Unlike traditional optimization methods, quantum-inspired AI makes use of the power of quantum computing principles to explore complex parameter spaces much more effectively, yielding far superior optimization results.Our experiments further reveal that such models yield higher accuracy in their performance predictions and by orders of magnitudes reduce both time and computational resources for optimization.The proposed approach can fulfill this by integrating real data, thus making the entire approach practical and robust.Overcoming these challenges will help the semiconductor industries meet the everincreasing demand in speed, size, and energy efficiency.This paper researches the potential of quantuminspired AI to revolutionize the fields of semiconductor design and manufacture for next-generation electronic technology.

International Research Journal of Modernization in Engineering Technology and Science•Feb 10, 2025•1 citation

Achieving Sub-Exponential Speedup in Gate-Based Quantum Computing for Quadratic Unconstrained Binary Optimization

Tseng Ying-Wei, Kao Yu-Ting, Yeong-Jar Chang +2 more

Recent quantum-inspired methods based on the Simulated Annealing (SA) algorithm have shown strong potential for solving combinatorial optimization problems. However, Grover's algorithm [1] in gate-based quantum computing offers only a quadratic speedup, which remains impractical for large problem sizes. This paper proposes a hybrid approach that integrates SA with Grover's algorithm to achieve sub-exponential speedup, thereby improving its industrial applicability. In enzyme fermentation, variables such as temperature, stirring, wait time, pH, tryptophan, rice flour and so on are encoded by 625 binary parameters, defining the space of possible enzyme formulations. We aim to find a binary configuration that maximizes the active ingredient, formulated as a 625-bit QUBO which is generated by historical experiments and AI techniques. Minimizing the QUBO cost corresponds to maximizing the active ingredient. This case study demonstrates that our hybrid method achieves sub-exponential speedup through gate-based quantum computing.

arXiv:2510.15334•Oct 17, 2025•1 citation

The Application of Artificial Intelligence in Quantum Mechanics: Challenges and Opportunities

Nguyen Minh Tu, Tran Thi Lan, Arnes Yuli Vandika

The intersection of artificial intelligence (AI) and quantum mechanics represents a frontier of scientific exploration, offering the potential to revolutionize our understanding of quantum systems. Despite the promise, significant challenges remain in effectively integrating AI techniques within quantum mechanics frameworks. This study aims to investigate the applications of AI in quantum mechanics, identifying both the challenges and opportunities presented by this interdisciplinary approach. The focus is on understanding how AI can enhance quantum simulations, optimize computations, and improve experimental designs. A comprehensive literature review was conducted, analyzing recent advancements in AI algorithms applied to quantum mechanics. Case studies were examined to illustrate successful implementations and the limitations encountered. Key metrics for evaluation included computational efficiency, accuracy, and scalability. Findings indicate that AI techniques, particularly machine learning and neural networks, can significantly expedite quantum simulations and enhance predictive accuracy. However, challenges such as data sparsity, interpretability of AI models, and the integration of AI with quantum algorithms were identified as significant barriers to progress. This research highlights the transformative potential of AI in advancing quantum mechanics while acknowledging the inherent challenges. Addressing these challenges will require collaborative efforts across disciplines, paving the way for innovative solutions that leverage AI to deepen our understanding of quantum phenomena and improve technological applications.

Research of Scientia Naturalis•Dec 27, 2024•1 citation

Entangling Intelligence: AI-Quantum Crossovers and Perspectives

Zhuo Chen, Di Luo

The intersection of artificial intelligence (AI) and quantum physics has sparked significant advancements in both fields. This paper first reviews the application of AI techniques, particularly neural networks, to quantum simulation. We discuss key developments in representing quantum states, efficient sampling methods, and optimization techniques for ground states and dynamics. The review also explores how quantum principles enhances AI algorithms, including quantum-inspired neural architectures and physics-based optimization methods. We highlight challenges and open questions in this rapidly evolving interdisciplinary field, emphasizing the potential for future innovations that combine AI and quantum approaches to address complex problems in both domains.

IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)•Oct 28, 2024•3 citations

Quantum Multiphysics Simulation Optimization

Jincheng Zhang

Quantum Multiphysics Simulation Optimization is a novel approach to accelerating and improving the efficiency of multi-physics simulations. Traditional methods often suffer from computational bottlenecks, limiting the scope and speed of simulations. This research introduces a new optimization algorithm predicated on quantum simulation principles, designed to significantly reduce simulation time and computational costs by intelligently manipulating the simulation process. The core mechanism leverages the unique quantum properties of the simulation to guide optimization, leading to improved accuracy and enhanced overall efficiency. This paper details the algorithm's design, implementation, and preliminary experimental results demonstrating its potential to revolutionize multi-physics simulation workflows.

•Aug 29, 2026•0 citations

Quantum-Inspired Optimization for Complex Systems

Jincheng Zhang

Quantum-inspired optimization aims to improve the performance of complex optimization problems by incorporating principles from quantum mechanics. This paper explores the application of quantum-like concepts, such as superposition and entanglement, to enhance the efficiency of optimization algorithms. We present a novel quantum-inspired optimization framework designed to address the challenges inherent in complex systems, offering a fundamentally different approach compared to traditional optimization methods. The core mechanism focuses on leveraging these quantum principles to achieve improved solution paths and faster convergence. This research contributes to the advancement of optimization techniques with the potential for significant gains in the solution of challenging problems across diverse fields.

•Sep 5, 2026•0 citations
This paper introduces a new method that combines Artificial Intelligence (AI) and quantum-inspired techniques to improve the efficiency of multi-variable optimization experiments. By using advanced software simulations, this approach significantly reduces the time and cost compared to traditional physical experiments. The research focuses on enzyme fermentation, demonstrating that this method can achieve better results with fewer experiments. The findings highlight the potential of this approach to more effectively identify optimal formulations, leading to advancements in enzyme fermentation and other fields that require complex optimization. Initially, the Active Ingredients (AIN) could not be improved even after 600 experiments. However, by adopting the method outlined in this paper, we were able to identify a better formula in just 405 experiments. This resulted in an increase of AIN from 8481 to 10068, representing an improvement of 18.7%.
The rapid advance in semiconductor technology requires novelty in approach to improve device performance and efficiency.This paper discusses the use of quantum-inspired AI models as a state-of-the-art solution for the optimization of semiconductor devices.We create and train these AI models with the help of real datasets to make accurate predictions and improvements in important performance parameters of different semiconductor components.Unlike traditional optimization methods, quantum-inspired AI makes use of the power of quantum computing principles to explore complex parameter spaces much more effectively, yielding far superior optimization results.Our experiments further reveal that such models yield higher accuracy in their performance predictions and by orders of magnitudes reduce both time and computational resources for optimization.The proposed approach can fulfill this by integrating real data, thus making the entire approach practical and robust.Overcoming these challenges will help the semiconductor industries meet the everincreasing demand in speed, size, and energy efficiency.This paper researches the potential of quantuminspired AI to revolutionize the fields of semiconductor design and manufacture for next-generation electronic technology.
Recent quantum-inspired methods based on the Simulated Annealing (SA) algorithm have shown strong potential for solving combinatorial optimization problems. However, Grover's algorithm [1] in gate-based quantum computing offers only a quadratic speedup, which remains impractical for large problem sizes. This paper proposes a hybrid approach that integrates SA with Grover's algorithm to achieve sub-exponential speedup, thereby improving its industrial applicability. In enzyme fermentation, variables such as temperature, stirring, wait time, pH, tryptophan, rice flour and so on are encoded by 625 binary parameters, defining the space of possible enzyme formulations. We aim to find a binary configuration that maximizes the active ingredient, formulated as a 625-bit QUBO which is generated by historical experiments and AI techniques. Minimizing the QUBO cost corresponds to maximizing the active ingredient. This case study demonstrates that our hybrid method achieves sub-exponential speedup through gate-based quantum computing.
The intersection of artificial intelligence (AI) and quantum mechanics represents a frontier of scientific exploration, offering the potential to revolutionize our understanding of quantum systems. Despite the promise, significant challenges remain in effectively integrating AI techniques within quantum mechanics frameworks. This study aims to investigate the applications of AI in quantum mechanics, identifying both the challenges and opportunities presented by this interdisciplinary approach. The focus is on understanding how AI can enhance quantum simulations, optimize computations, and improve experimental designs. A comprehensive literature review was conducted, analyzing recent advancements in AI algorithms applied to quantum mechanics. Case studies were examined to illustrate successful implementations and the limitations encountered. Key metrics for evaluation included computational efficiency, accuracy, and scalability. Findings indicate that AI techniques, particularly machine learning and neural networks, can significantly expedite quantum simulations and enhance predictive accuracy. However, challenges such as data sparsity, interpretability of AI models, and the integration of AI with quantum algorithms were identified as significant barriers to progress. This research highlights the transformative potential of AI in advancing quantum mechanics while acknowledging the inherent challenges. Addressing these challenges will require collaborative efforts across disciplines, paving the way for innovative solutions that leverage AI to deepen our understanding of quantum phenomena and improve technological applications.
The intersection of artificial intelligence (AI) and quantum physics has sparked significant advancements in both fields. This paper first reviews the application of AI techniques, particularly neural networks, to quantum simulation. We discuss key developments in representing quantum states, efficient sampling methods, and optimization techniques for ground states and dynamics. The review also explores how quantum principles enhances AI algorithms, including quantum-inspired neural architectures and physics-based optimization methods. We highlight challenges and open questions in this rapidly evolving interdisciplinary field, emphasizing the potential for future innovations that combine AI and quantum approaches to address complex problems in both domains.
Quantum Multiphysics Simulation Optimization is a novel approach to accelerating and improving the efficiency of multi-physics simulations. Traditional methods often suffer from computational bottlenecks, limiting the scope and speed of simulations. This research introduces a new optimization algorithm predicated on quantum simulation principles, designed to significantly reduce simulation time and computational costs by intelligently manipulating the simulation process. The core mechanism leverages the unique quantum properties of the simulation to guide optimization, leading to improved accuracy and enhanced overall efficiency. This paper details the algorithm's design, implementation, and preliminary experimental results demonstrating its potential to revolutionize multi-physics simulation workflows.
Quantum-inspired optimization aims to improve the performance of complex optimization problems by incorporating principles from quantum mechanics. This paper explores the application of quantum-like concepts, such as superposition and entanglement, to enhance the efficiency of optimization algorithms. We present a novel quantum-inspired optimization framework designed to address the challenges inherent in complex systems, offering a fundamentally different approach compared to traditional optimization methods. The core mechanism focuses on leveraging these quantum principles to achieve improved solution paths and faster convergence. This research contributes to the advancement of optimization techniques with the potential for significant gains in the solution of challenging problems across diverse fields.