© 2026 Aqora Quantum S.A.S.

Terms Privacy Legal Notice

Electronics

Quantum Dynamic Optimization Algorithm for Neural Architecture Search on Image Classification

Jin Jin, Qian Zhang, Jia He, Hongnian Yu

Published Nov 30, 2022• 5 citations

Abstract

Deep neural networks have proven to be effective in solving computer vision and natural language processing problems. To fully leverage its power, manually designed network templates, i.e., Residual Networks, are introduced to deal with various vision and natural language tasks. These hand-crafted neural networks rely on a large number of parameters, which are both data-dependent and laborious. On the other hand, architectures suitable for specific tasks have also grown exponentially with their size and topology, which prohibits brute force search. To address these challenges, this paper proposes a quantum dynamic optimization algorithm to find the optimal structure for a candidate network using Quantum Dynamic Neural Architecture Search (QDNAS). Specifically, the proposed quantum dynamics optimization algorithm is used to search for meaningful architectures for vision tasks and dedicated rules to express and explore the search space. The proposed quantum dynamics optimization algorithm treats the iterative evolution process of the optimization over time as a quantum dynamic process. The tunneling effect and potential barrier estimation in quantum mechanics can effectively promote the evolution of the optimization algorithm to the global optimum. Extensive experiments on four benchmarks demonstrate the effectiveness of QDNAS, which is consistently better than all baseline methods in image classification tasks. Furthermore, an in-depth analysis is conducted on the searchable networks that provide inspiration for the design of other image classification networks.

DOI: 10.3390/electronics11233969

Related papers

Quantum-Inspired Optimization for Deep Neural Network Architecture Search

Jincheng Zhang

The process of designing optimal deep neural network architectures is a computationally expensive and often manual task. Traditional gradient-based optimization methods struggle to efficiently explore the vast architectural search space, leading to sub-optimal designs. This research proposes a novel approach leveraging quantum-inspired optimization techniques, specifically quantum annealing, to accelerate the architecture search process. We formulate the architecture search problem as a minimization task within a quantum annealing landscape. The objective function is designed to reflect the performance metrics of a given neural network architecture. Our approach offers a potentially more efficient method for discovering high-performing architectures by harnessing the principles of quantum mechanics, particularly superposition and tunneling, to navigate the complex search space. The core claim is that gradient-based optimization is often inefficient for this task, and quantum annealing provides a viable alternative. This paper outlines the theoretical framework and proposes an initial methodology for applying quantum annealing to deep neural network architecture search.

•Sep 5, 2026•0 citations

Quantum-Inspired Optimization of Deep Neural Network Architectures

Jincheng Zhang

The design of deep neural network (DNN) architectures is a complex and computationally intensive task. Traditional methods often rely on manual tuning or random search, which are inefficient in exploring the exponentially large architectural space. This paper proposes a novel approach to DNN architecture optimization leveraging quantum-inspired algorithms. Specifically, we explore the application of algorithms inspired by quantum annealing and quantum Monte Carlo methods to efficiently search for optimal DNN configurations. Our framework aims to minimize the trade-off between accuracy, latency, and energy consumption – key considerations in real-world DNN deployments. We present a theoretical framework and outline a methodology for integrating these quantum-inspired techniques. The core idea is to map the architectural design problem onto a suitable quantum system, allowing for the parallel exploration of potential solutions. This research provides a new direction for automated DNN design, potentially leading to significant improvements in performance and efficiency.

•Sep 2, 2026•0 citations

Adaptive Quantum Neural Networks: Dynamic Architecture Optimization

Jincheng Zhang

This paper introduces an adaptive quantum neural network architecture optimization algorithm, termed "Quantum Self-Adaptation Adjustment" (QSAA). We propose a novel approach to automatically tune the network's structure and parameters, leveraging the inherent dynamic properties of quantum neural networks. The core mechanism centers around a "Quantum Self-Adaptation Adjustment" (QSAA) process, which employs quantum computing principles to learn more complex network configurations and parameter adjustments. The algorithm's design aims to improve model performance and generalization capabilities compared to traditional neural network approaches. We present preliminary results demonstrating the effectiveness of QSAA in optimizing network structure for a specific classification task, highlighting its potential for enhancing deep learning models.

•Aug 31, 2026•0 citations

Quantum-Inspired Optimization of Neural Network Architecture

Jincheng Zhang

This paper explores a novel approach to neural network architecture optimization inspired by quantum superposition and measurement. Traditional neural network architecture search methods, such as reinforcement learning or evolutionary algorithms, often suffer from computational bottlenecks and slow convergence rates. We propose a genetic algorithm that leverages quantum-inspired probability amplitudes to represent and evaluate neural network architectures. Each architecture is assigned a set of probability amplitudes, reflecting the potential for success. Through a simulated measurement process, the algorithm dynamically adjusts these amplitudes, favoring architectures with higher potential and accelerating the search for optimal configurations. The core idea is that quantum superposition allows us to explore a vast solution space concurrently, while the measurement process mimics the collapse of the wave function, focusing the search on promising candidates. This approach demonstrates the potential to significantly reduce the time and resources required for neural network architecture design, paving the way for more efficient and powerful deep learning models. We present a detailed theoretical framework and outline the key components of the algorithm, emphasizing its ability to mimic quantum phenomena for architectural optimization.

•Aug 31, 2026•0 citations

Quantum Walk-Based Optimization of Neural Network Architectures

Jincheng Zhang

This paper investigates the application of quantum walks to the optimization of neural network architectures, a problem traditionally addressed through computationally intensive classical methods. The core idea is to leverage the inherent parallelism and probabilistic nature of quantum walks to efficiently explore the vast architecture space of neural networks. We propose a framework where a quantum walk is performed on a graph representing candidate neural network architectures. The walk's evolution is governed by a Hamiltonian operator designed to encourage the selection of architectures with desirable performance characteristics, as measured by a predefined objective function. Through theoretical analysis and conceptual design, we demonstrate the potential for quantum walks to achieve significant speedups compared to traditional NAS algorithms, potentially realizing exponential improvements in the search process. The exploration of this approach opens new avenues for designing high-performing neural networks with reduced computational costs.

•Sep 2, 2026•0 citations

Neural Architecture Search for Quantum Autoencoders

Hibah Agha, Samuel Yen-Chi Chen, Huan-Hsin Tseng +1 more

In recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously, quantum computing (QC) promises to address classically intractable problems via quantum parallelism, motivating research in quantum machine learning (QML). Among QML techniques, quantum autoencoders show promise for compressing high-dimensional quantum and classical data. However, designing effective quantum circuit architectures for quantum autoencoders remains challenging due to the complexity of selecting gates, arranging circuit layers, and tuning parameters. This paper proposes a neural architecture search (NAS) framework that automates the design of quantum autoencoders using a genetic algorithm (GA). By systematically evolving variational quantum circuit (VQC) configurations, our method seeks to identify high-performing hybrid quantum-classical autoencoders for data reconstruction without becoming trapped in local minima. We demonstrate effectiveness on image datasets, highlighting the potential of quantum autoencoders for efficient feature extraction within a noise-prone, near-term quantum era. Our approach lays a foundation for broader application of genetic algorithms to quantum architecture search, aiming for a robust, automated method that can adapt to varied data and hardware constraints.

quant-pharXiv:2511.19246•Nov 25, 2025•0 citations

Deep neural networks have proven to be effective in solving computer vision and natural language processing problems. To fully leverage its power, manually designed network templates, i.e., Residual Networks, are introduced to deal with various vision and natural language tasks. These hand-crafted neural networks rely on a large number of parameters, which are both data-dependent and laborious. On the other hand, architectures suitable for specific tasks have also grown exponentially with their size and topology, which prohibits brute force search. To address these challenges, this paper proposes a quantum dynamic optimization algorithm to find the optimal structure for a candidate network using Quantum Dynamic Neural Architecture Search (QDNAS). Specifically, the proposed quantum dynamics optimization algorithm is used to search for meaningful architectures for vision tasks and dedicated rules to express and explore the search space. The proposed quantum dynamics optimization algorithm treats the iterative evolution process of the optimization over time as a quantum dynamic process. The tunneling effect and potential barrier estimation in quantum mechanics can effectively promote the evolution of the optimization algorithm to the global optimum. Extensive experiments on four benchmarks demonstrate the effectiveness of QDNAS, which is consistently better than all baseline methods in image classification tasks. Furthermore, an in-depth analysis is conducted on the searchable networks that provide inspiration for the design of other image classification networks.

The process of designing optimal deep neural network architectures is a computationally expensive and often manual task. Traditional gradient-based optimization methods struggle to efficiently explore the vast architectural search space, leading to sub-optimal designs. This research proposes a novel approach leveraging quantum-inspired optimization techniques, specifically quantum annealing, to accelerate the architecture search process. We formulate the architecture search problem as a minimization task within a quantum annealing landscape. The objective function is designed to reflect the performance metrics of a given neural network architecture. Our approach offers a potentially more efficient method for discovering high-performing architectures by harnessing the principles of quantum mechanics, particularly superposition and tunneling, to navigate the complex search space. The core claim is that gradient-based optimization is often inefficient for this task, and quantum annealing provides a viable alternative. This paper outlines the theoretical framework and proposes an initial methodology for applying quantum annealing to deep neural network architecture search.

The design of deep neural network (DNN) architectures is a complex and computationally intensive task. Traditional methods often rely on manual tuning or random search, which are inefficient in exploring the exponentially large architectural space. This paper proposes a novel approach to DNN architecture optimization leveraging quantum-inspired algorithms. Specifically, we explore the application of algorithms inspired by quantum annealing and quantum Monte Carlo methods to efficiently search for optimal DNN configurations. Our framework aims to minimize the trade-off between accuracy, latency, and energy consumption – key considerations in real-world DNN deployments. We present a theoretical framework and outline a methodology for integrating these quantum-inspired techniques. The core idea is to map the architectural design problem onto a suitable quantum system, allowing for the parallel exploration of potential solutions. This research provides a new direction for automated DNN design, potentially leading to significant improvements in performance and efficiency.

This paper introduces an adaptive quantum neural network architecture optimization algorithm, termed "Quantum Self-Adaptation Adjustment" (QSAA). We propose a novel approach to automatically tune the network's structure and parameters, leveraging the inherent dynamic properties of quantum neural networks. The core mechanism centers around a "Quantum Self-Adaptation Adjustment" (QSAA) process, which employs quantum computing principles to learn more complex network configurations and parameter adjustments. The algorithm's design aims to improve model performance and generalization capabilities compared to traditional neural network approaches. We present preliminary results demonstrating the effectiveness of QSAA in optimizing network structure for a specific classification task, highlighting its potential for enhancing deep learning models.

This paper explores a novel approach to neural network architecture optimization inspired by quantum superposition and measurement. Traditional neural network architecture search methods, such as reinforcement learning or evolutionary algorithms, often suffer from computational bottlenecks and slow convergence rates. We propose a genetic algorithm that leverages quantum-inspired probability amplitudes to represent and evaluate neural network architectures. Each architecture is assigned a set of probability amplitudes, reflecting the potential for success. Through a simulated measurement process, the algorithm dynamically adjusts these amplitudes, favoring architectures with higher potential and accelerating the search for optimal configurations. The core idea is that quantum superposition allows us to explore a vast solution space concurrently, while the measurement process mimics the collapse of the wave function, focusing the search on promising candidates. This approach demonstrates the potential to significantly reduce the time and resources required for neural network architecture design, paving the way for more efficient and powerful deep learning models. We present a detailed theoretical framework and outline the key components of the algorithm, emphasizing its ability to mimic quantum phenomena for architectural optimization.

This paper investigates the application of quantum walks to the optimization of neural network architectures, a problem traditionally addressed through computationally intensive classical methods. The core idea is to leverage the inherent parallelism and probabilistic nature of quantum walks to efficiently explore the vast architecture space of neural networks. We propose a framework where a quantum walk is performed on a graph representing candidate neural network architectures. The walk's evolution is governed by a Hamiltonian operator designed to encourage the selection of architectures with desirable performance characteristics, as measured by a predefined objective function. Through theoretical analysis and conceptual design, we demonstrate the potential for quantum walks to achieve significant speedups compared to traditional NAS algorithms, potentially realizing exponential improvements in the search process. The exploration of this approach opens new avenues for designing high-performing neural networks with reduced computational costs.

In recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously, quantum computing (QC) promises to address classically intractable problems via quantum parallelism, motivating research in quantum machine learning (QML). Among QML techniques, quantum autoencoders show promise for compressing high-dimensional quantum and classical data. However, designing effective quantum circuit architectures for quantum autoencoders remains challenging due to the complexity of selecting gates, arranging circuit layers, and tuning parameters. This paper proposes a neural architecture search (NAS) framework that automates the design of quantum autoencoders using a genetic algorithm (GA). By systematically evolving variational quantum circuit (VQC) configurations, our method seeks to identify high-performing hybrid quantum-classical autoencoders for data reconstruction without becoming trapped in local minima. We demonstrate effectiveness on image datasets, highlighting the potential of quantum autoencoders for efficient feature extraction within a noise-prone, near-term quantum era. Our approach lays a foundation for broader application of genetic algorithms to quantum architecture search, aiming for a robust, automated method that can adapt to varied data and hardware constraints.