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

Evaluating the Influence of Adam and Ada-delta Optimizers on Varied Qubit Configurations in QLSTM Models

Sachin Namdeo, Manisha J. Nene

Published Apr 12, 2024• 0 citations
Publisher

Abstract

Abstract Quantum Machine Learning (QML) holds the promise of making significant changes to how Artificial Intelligence (AI) functions. A notable breakthrough in this field is the development of Quantum Long Short- Term Memory (QLSTM) networks, which exhibit faster learning compared to standard Long Short-Term Memory (LSTM) networks. QLSTM builds upon classical LSTM networks but incorporates principles of quantum computation, allowing it to explore superposition and entanglement for parallel information processing. By using quantum bits (qubits), QLSTM potentially offers advantages for specific machine learning tasks. Despite its potential, QLSTM remains a relatively unexplored area within QML, particularly regarding its dependency on the number of qubits and the impact of different optimizers on its performance. This study aims to reveal valuable insights to enhance QLSTM and explore its potential applications in AI. The study focuses on two main aspects. Firstly, exploring how the Adam and Ada-delta optimization methods improve QLSTM models, playing a role in refining the performance of the quantum model. Secondly, the study delves into the consequences of using varying numbers of qubits in the QLSTM model. Understanding how the quantity of qubits influences performance is essential for optimizing the network's efficiency. By addressing these aspects, the study seeks to contribute to advancing QLSTM and offering valuable knowledge for its potential applications in the AI field. The findings may suggest exciting opportunities for future research on QLSTM models, prompting exploration into optimization strategies, regularization techniques, and quantum data augmentation. Additionally, the study emphasizes the importance of leveraging ensemble learning and validating applicability in real-world quantum computing scenarios. These efforts are crucial for advancing understanding and maximizing potential in the continually evolving landscape of quantum computing applications.

DOI
10.21203/rs.3.rs-4241406/v1

Related papers

Quantum Long Short-Term Memory for Sequence Prediction

Belkacem Chikhaoui

Quantum machine learning (QML) offers new perspectives for modeling complex sequential data by leveraging the computational advantages of quantum computing. In this work, we explore the application of Quantum Long Short-Term Memory (QLSTM) networks for sequence prediction tasks. By integrating parameterized quantum circuits within the classical LSTM architecture, QLSTM models exploit quantum parallelism and entanglement to learn temporal dependencies in data more efficiently. We evaluate the performance of QLSTM on synthetic and real-world sequence prediction tasks and compare it with its classical counterpart. The results demonstrate that QLSTM models achieve competitive performance with fewer trainable parameters, indicating their potential as lightweight and efficient models for sequence learning and prediction.

IEEE/ACS International Conference on Computer Systems and Applications (AICCSA)•Oct 19, 2025•0 citations

Quantum long short-term memory for drug discovery

Liang Zhang, Yin Xu, Mohan Wu +2 more

Abstract Quantum computing combined with machine learning (ML) is a highly promising research area, with numerous studies demonstrating that quantum machine learning (QML) is expected to solve scientific problems more effectively than classical ML. In this work, we present Quantum Long Short-Term Memory (QLSTM), a QML architecture, and demonstrate its effectiveness in drug discovery. We evaluate QLSTM on five benchmark datasets (BBBP, BACE, SIDER, BCAP37, T-47D), and observe consistent performance gains over classical LSTM, with ROC-AUC improvements ranging from 3% to over 6%. Furthermore, QLSTM exhibits improved predictive accuracy as the number of qubits increases, and faster convergence than classical LSTM under the same training conditions. Notably, QLSTM maintains strong robustness against quantum computer noise, outperforming noise-free classical LSTM in certain settings. These findings highlight the potential of QLSTM as a scalable and noise-resilient model for scientific applications, particularly as quantum hardware continues to advance in qubit capacity and fidelity.

arXiv:2407.19852•EPJ Quantum Technology•Jan 12, 2026•10 citations

Implementation Guidelines and Innovations in Quantum LSTM Networks

Yifan Zhou, Chong Xu, Mingi Song +1 more

Abstract The rapid evolution of artificial intelligence has driven interest in Long Short-Term Memory (LSTM) networks for their effectiveness in processing sequential data. However, traditional LSTMs are limited by issues such as the vanishing gradient problem and high computational demands. Quantum computing offers a potential solution to these challenges, promising advancements in computational efficiency through the unique properties of qubits, such as superposition and entanglement. This paper presents a theoretical analysis and an implementation plan for a Quantum LSTM (qLSTM) model, which seeks to integrate quantum computing principles with traditional LSTM networks. While the proposed model aims to address the limitations of classical LSTMs, this study focuses primarily on the theoretical aspects and the implementation framework. The actual architecture and its practical effectiveness in enhancing sequential data processing remain to be developed and demonstrated in future work.

arXiv:2406.08982•Oct 10, 2024•12 citations

Application of Qubits in Artificial Intelligence and Machine Learning

S. Nalini, Amit Kumar Tyagi, Shrikant Tiwari +1 more

The emergence of quantum computing has unlocked fresh opportunities for the realms of artificial intelligence (AI) and machine learning (ML). This section delves into the revolutionary uses of qubits, the basic building blocks of quantum computing, in conjunction with AI and ML. Leveraging the principles of superposition and entanglement, qubits offer unparalleled computational capabilities, poised to transform our approach to intricate problem-solving and data analysis. Presently, quantum machine learning (QML) methodologies exhibit potential across a wide array of fields, spanning from drug discovery and financial modeling to natural language processing. These applications have the potential to redefine the benchmarks of AI and ML performance. Furthermore, this chapter elucidates the fundamental principles of qubits and quantum computing, underscoring their ability to represent and process vast amounts of information simultaneously. It also elucidates how qubits have the potential to tackle problems that were previously deemed insurmountable by classical computers, encompassing optimization tasks, cryptographic puzzles, and data analysis. We delve into the role of qubits in bolstering the resilience and efficiency of AI systems, encompassing quantum neural networks, quantum reinforcement learning, and quantum-enhanced decision-making mechanisms. Last, we expound on specific applications in AI and ML, where qubits are on the brink of ushering in a new era of capabilities.

Auerbach Publications eBooks•Mar 3, 2025•2 citations

Quantum Machine Learning Opportunities for Scalable AI

Rohan Shahane and Satya Prakash

Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the computational power of quantum computing with machine learning techniques to address the scalability challenges faced by classical AI systems. As datasets and models grow in complexity, traditional machine learning algorithms encounter limitations related to processing speed, accuracy, and resource efficiency. This research explores the potential of QML to overcome these barriers by leveraging quantum algorithms such as Quantum Approximate Optimization Algorithms (QAOA), Quantum Support Vector Machines (QSVM), and Quantum Neural Networks (QNNs) to enhance the scalability and efficiency of AI applications. Through a combination of literature review, algorithm simulation, and hybrid quantum-classical approaches, the study evaluates the speedup, accuracy improvements, and resource efficiency that quantum-enhanced models can offer. The research also investigates practical applications of QML in domains such as healthcare, finance, and climate science. Despite significant advancements, challenges related to quantum hardware, error correction, and noise remain, which will be discussed alongside strategies for overcoming these issues. The findings suggest that while quantum machine learning holds immense potential, its full impact on scalable AI will require further advancements in quantum computing and its integration with classical systems.

Journal of validation technology•Jul 15, 2025•0 citations

Integration of Quantum Computing and Machine Learning: Promoting Optimization, Pattern Detection, and Computational Efficiency

R. C. Thivyarathi, V. Samuthira Pandi, Abdelhalim Mohammad Jubran +3 more

Quantum computing and machine learning (QML) have emerged as a revolutionary per approach to solve complex computational problems that classical systems are unable to. The use of superposition, entanglement, and quantum parallelism helps analyze data up to ten times faster than in a non-quantum manner, enhancing optimization, pattern identification, and computational efficiency. This paper studies the potential of quantum algorithms and machine learning in areas of categorization, grouping, and regression in banking, healthcare, cybersecurity, and scientific simulations. QML shines when it comes to generalizing low cost over high-dimensional data spaces. State-of-theart quantum-enhanced algorithms (QSVMs, VQCs, QBMs) yield better solutions to complex pattern recognition problems. Quantum-inspired neural networks accelerate deep learning architectures by optimizing gradient descent and decreasing training periods. The following research explores how QML enables a potentially computationally efficient solution to combinatorial optimization problems in the realms of logistics, cryptography, and artificial intelligence through quantum annealing and hybrid quantumclassical models. QML is still not able to deploy for the hardware limitations, noise sensitive nature, and quantum decoherence, despite promising results. The study underscores the importance of error correction procedures, as well as noise-resilient quantum circuits, and ultimately their scaling to full computers to reconcile theoretical promise with real-world application. It explores the ability of hybrid quantum-classical models to provide near-term developed applications as a bridge to realizable quantum computation. In this article, researchers present a thorough overview of quantum algorithms, reduced computational complexity, and practical applications, furthering the field of quantumenhanced machine learning. Industries might be revolutionized with quantum computers and AI-based decision-making systems working together with unprecedented computational power. In particular, quantum algorithms, hardware, and quantum cloud computing platforms must be a research focus area to ensure that quantum will deliver the most significant advances in AI.

International Conference on Smart Structures and Systems (ICSSS)•Dec 12, 2025•3 citations
Abstract Quantum Machine Learning (QML) holds the promise of making significant changes to how Artificial Intelligence (AI) functions. A notable breakthrough in this field is the development of Quantum Long Short- Term Memory (QLSTM) networks, which exhibit faster learning compared to standard Long Short-Term Memory (LSTM) networks. QLSTM builds upon classical LSTM networks but incorporates principles of quantum computation, allowing it to explore superposition and entanglement for parallel information processing. By using quantum bits (qubits), QLSTM potentially offers advantages for specific machine learning tasks. Despite its potential, QLSTM remains a relatively unexplored area within QML, particularly regarding its dependency on the number of qubits and the impact of different optimizers on its performance. This study aims to reveal valuable insights to enhance QLSTM and explore its potential applications in AI. The study focuses on two main aspects. Firstly, exploring how the Adam and Ada-delta optimization methods improve QLSTM models, playing a role in refining the performance of the quantum model. Secondly, the study delves into the consequences of using varying numbers of qubits in the QLSTM model. Understanding how the quantity of qubits influences performance is essential for optimizing the network's efficiency. By addressing these aspects, the study seeks to contribute to advancing QLSTM and offering valuable knowledge for its potential applications in the AI field. The findings may suggest exciting opportunities for future research on QLSTM models, prompting exploration into optimization strategies, regularization techniques, and quantum data augmentation. Additionally, the study emphasizes the importance of leveraging ensemble learning and validating applicability in real-world quantum computing scenarios. These efforts are crucial for advancing understanding and maximizing potential in the continually evolving landscape of quantum computing applications.
Quantum machine learning (QML) offers new perspectives for modeling complex sequential data by leveraging the computational advantages of quantum computing. In this work, we explore the application of Quantum Long Short-Term Memory (QLSTM) networks for sequence prediction tasks. By integrating parameterized quantum circuits within the classical LSTM architecture, QLSTM models exploit quantum parallelism and entanglement to learn temporal dependencies in data more efficiently. We evaluate the performance of QLSTM on synthetic and real-world sequence prediction tasks and compare it with its classical counterpart. The results demonstrate that QLSTM models achieve competitive performance with fewer trainable parameters, indicating their potential as lightweight and efficient models for sequence learning and prediction.
Abstract Quantum computing combined with machine learning (ML) is a highly promising research area, with numerous studies demonstrating that quantum machine learning (QML) is expected to solve scientific problems more effectively than classical ML. In this work, we present Quantum Long Short-Term Memory (QLSTM), a QML architecture, and demonstrate its effectiveness in drug discovery. We evaluate QLSTM on five benchmark datasets (BBBP, BACE, SIDER, BCAP37, T-47D), and observe consistent performance gains over classical LSTM, with ROC-AUC improvements ranging from 3% to over 6%. Furthermore, QLSTM exhibits improved predictive accuracy as the number of qubits increases, and faster convergence than classical LSTM under the same training conditions. Notably, QLSTM maintains strong robustness against quantum computer noise, outperforming noise-free classical LSTM in certain settings. These findings highlight the potential of QLSTM as a scalable and noise-resilient model for scientific applications, particularly as quantum hardware continues to advance in qubit capacity and fidelity.
Abstract The rapid evolution of artificial intelligence has driven interest in Long Short-Term Memory (LSTM) networks for their effectiveness in processing sequential data. However, traditional LSTMs are limited by issues such as the vanishing gradient problem and high computational demands. Quantum computing offers a potential solution to these challenges, promising advancements in computational efficiency through the unique properties of qubits, such as superposition and entanglement. This paper presents a theoretical analysis and an implementation plan for a Quantum LSTM (qLSTM) model, which seeks to integrate quantum computing principles with traditional LSTM networks. While the proposed model aims to address the limitations of classical LSTMs, this study focuses primarily on the theoretical aspects and the implementation framework. The actual architecture and its practical effectiveness in enhancing sequential data processing remain to be developed and demonstrated in future work.
The emergence of quantum computing has unlocked fresh opportunities for the realms of artificial intelligence (AI) and machine learning (ML). This section delves into the revolutionary uses of qubits, the basic building blocks of quantum computing, in conjunction with AI and ML. Leveraging the principles of superposition and entanglement, qubits offer unparalleled computational capabilities, poised to transform our approach to intricate problem-solving and data analysis. Presently, quantum machine learning (QML) methodologies exhibit potential across a wide array of fields, spanning from drug discovery and financial modeling to natural language processing. These applications have the potential to redefine the benchmarks of AI and ML performance. Furthermore, this chapter elucidates the fundamental principles of qubits and quantum computing, underscoring their ability to represent and process vast amounts of information simultaneously. It also elucidates how qubits have the potential to tackle problems that were previously deemed insurmountable by classical computers, encompassing optimization tasks, cryptographic puzzles, and data analysis. We delve into the role of qubits in bolstering the resilience and efficiency of AI systems, encompassing quantum neural networks, quantum reinforcement learning, and quantum-enhanced decision-making mechanisms. Last, we expound on specific applications in AI and ML, where qubits are on the brink of ushering in a new era of capabilities.
Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the computational power of quantum computing with machine learning techniques to address the scalability challenges faced by classical AI systems. As datasets and models grow in complexity, traditional machine learning algorithms encounter limitations related to processing speed, accuracy, and resource efficiency. This research explores the potential of QML to overcome these barriers by leveraging quantum algorithms such as Quantum Approximate Optimization Algorithms (QAOA), Quantum Support Vector Machines (QSVM), and Quantum Neural Networks (QNNs) to enhance the scalability and efficiency of AI applications. Through a combination of literature review, algorithm simulation, and hybrid quantum-classical approaches, the study evaluates the speedup, accuracy improvements, and resource efficiency that quantum-enhanced models can offer. The research also investigates practical applications of QML in domains such as healthcare, finance, and climate science. Despite significant advancements, challenges related to quantum hardware, error correction, and noise remain, which will be discussed alongside strategies for overcoming these issues. The findings suggest that while quantum machine learning holds immense potential, its full impact on scalable AI will require further advancements in quantum computing and its integration with classical systems.
Quantum computing and machine learning (QML) have emerged as a revolutionary per approach to solve complex computational problems that classical systems are unable to. The use of superposition, entanglement, and quantum parallelism helps analyze data up to ten times faster than in a non-quantum manner, enhancing optimization, pattern identification, and computational efficiency. This paper studies the potential of quantum algorithms and machine learning in areas of categorization, grouping, and regression in banking, healthcare, cybersecurity, and scientific simulations. QML shines when it comes to generalizing low cost over high-dimensional data spaces. State-of-theart quantum-enhanced algorithms (QSVMs, VQCs, QBMs) yield better solutions to complex pattern recognition problems. Quantum-inspired neural networks accelerate deep learning architectures by optimizing gradient descent and decreasing training periods. The following research explores how QML enables a potentially computationally efficient solution to combinatorial optimization problems in the realms of logistics, cryptography, and artificial intelligence through quantum annealing and hybrid quantumclassical models. QML is still not able to deploy for the hardware limitations, noise sensitive nature, and quantum decoherence, despite promising results. The study underscores the importance of error correction procedures, as well as noise-resilient quantum circuits, and ultimately their scaling to full computers to reconcile theoretical promise with real-world application. It explores the ability of hybrid quantum-classical models to provide near-term developed applications as a bridge to realizable quantum computation. In this article, researchers present a thorough overview of quantum algorithms, reduced computational complexity, and practical applications, furthering the field of quantumenhanced machine learning. Industries might be revolutionized with quantum computers and AI-based decision-making systems working together with unprecedented computational power. In particular, quantum algorithms, hardware, and quantum cloud computing platforms must be a research focus area to ensure that quantum will deliver the most significant advances in AI.