Titre :	Enhancing Deep Learning with Quantum Computing: Exploring Hybrid Algorithms for Image Classification
Type de document :	document électronique
Auteurs :	Sabrina Lazeli ; Abdelouahab Moussaoui, Directeur de thèse
Editeur :	Setif:UFA
Année de publication :	2025
Importance :	1 vol (66 f .)
Format :	29 cm
Langues :	Anglais (eng)
Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Deep Learning Quantum Computing Image Classification
Index. décimale :	004 Informatique
Résumé :	This thesis explores the integration of quantum computing and deep learning paradigms to enhance image classification, with a particular focus on detecting Alzheimer’s disease stages from MRI images. An innovative hybrid architecture, combining the pre-trained ResNet50 neural network for feature extraction with a variational quantum circuit (VQC) for classification, was developed and evaluated on the Augmented Alzheimer MRI Dataset. This approach leverages the hierarchical feature extraction capabilities of classical convolutional neural networks and quantum properties such as superposition and entanglement to enhance the representation of complex patterns. The results demonstrate an overall accuracy of 97.35%, with outstanding performance in discriminating moderate stages (F1-score of 99.92%) and confirmed robustness through low variance. A comparative analysis with state-of-the-art approaches positions the proposed model among the top performers, highlighting the potential of hybrid quantum-classical algorithms to overcome computational limitations of classical methods, despite the constraints of current Noisy Intermediate-Scale Quantum NISQ devices. This work also proposes perspectives for optimizing quantum circuits and extending this approach to other medical imaging tasks, emphasizing the importance of future advancements in quantum hardware for practical implementation.
Note de contenu :	Sommaire General Introduction 8 0.1 Research problem ................................................................. 9 0.2 Objectives and contributions..................................................... 9 1 Theoretical Foundations of Quantum Computing 11 1.1 Principles of quantum computing ............................................... 12 1.1.1 Qubits and superposition ................................................ 12 1.1.2 Quantum entanglement .................................................. 12 1.1.3 Measurement .............................................................. 13 1.1.4 Quantum gates and circuits.............................................. 13 1.2 NISQ Devices: Noisy Intermediate-Scale Quantum Computing ............... 16 1.2.1 Special features of NISQ devices ........................................ 16 1.2.2 Hardware Architectures of NISQ Devices ............................... 17 1.3 Fundamental Quantum Algorithms ............................................. 18 1.3.1 Grover’s Algorithm ....................................................... 18 1.3.2 Shor’s Algorithm.......................................................... 18 2 Theoretical Foundations of Deep Learning 20 2.1 Principles of Deep learning ...................................................... 20 2.1.1 Artificial Neural Networks (ANN)....................................... 21 2.1.2 Convolutional Neural Networks (CNN) ................................. 21 2.1.3 Recurrent Neural Networks (RNN) ..................................... 23 2.1.4 Generative Adversarial Networks (GANs) .............................. 23 2.1.5 Current Challenges of Classical Deep Learning Approaches ........... 23 3 Hybrid Quantum Classical Algorithms 25 3.1 Structure of hybrid quantum-classical algorithms .............................. 25 3.1.1 Variational quantum circuit (VQC) ..................................... 27 3.1.2 Cost Functions ............................................................ 33 3.1.3 Optimization .............................................................. 34 3.2 Hybrid Quantum Classical Approaches for Image Classification: State of the Art ............................................................................ 35 3.2.1 Quantum Machine Learning for Image Classification introduced by Senokosov et al. ........................................................... 35 3.2.2 COVID-19 Detection Using Quantum Classical Transfer Learning Introduced by E. Acar and I. Yilmaz ................................... 36 3.2.3 Quantum Convolutional Neural Network for Image Classification Introduced by Al-Yousif et Al-Khateeb ................................ 37 3.2.4 Deep Ensemble learning and quantum machine learning approach for Alzheimer’s disease detection Introduced by A. J. Belay ......... 38 3.3 Challenges and Opportunities of Hybrid Quantum Classical Algorithms..... 38 3.3.1 The Challenges ........................................................... 39 3.3.2 The Advantages........................................................... 39 4 Hybrid Model for Image Classification: The Proposed Approach 41 4.1 Alzheimer’s Disease overview .................................................... 41 4.1.1 Symptoms and progression of the disease ............................... 41 4.1.2 Diagnostic methods and challenges of early detection ................. 41 4.1.3 Role of image classification in Alzheimer’s Diagnosis .................. 42 4.2 Hybrid Model Architecture ...................................................... 42 4.2.1 Classic Component: ResNet50........................................... 43 4.2.2 Quantum Component: Variational Quantum Circuit .................. 44 4.2.3 Hybrid Integration and Complete Architecture ........................ 45 4.3 DataSet and Preparation ......................................................... 47 4.3.1 Augmented Alzheimer MRI Dataset .................................... 47 4.3.2 Augmentation and Preprocessing........................................ 49 4.4 Training Configuration and Optimization....................................... 50 4.4.1 Multi-Scale Optimization Strategy ...................................... 50 4.4.2 Training configuration .................................................... 50 4.4.3 Hardware configuration .................................................. 51 4.4.4 Evaluation Metrics ....................................................... 51 5 Results and Analysis 54 5.1 Hybrid model performance ....................................................... 54 5.1.1 Final Results .............................................................. 54 5.2 Convergence Analysis............................................................. 55 5.2.1 Evolution of the Loss Function .......................................... 55 5.2.2 Evolution of the Accuracy Function..................................... 56 5.3 Performance Analysis by Class .................................................. 57 5.4 Validation of Hybrid Architecture ............................................... 59 5.4.1 State of the Art Comparison for Alzheimer’s Disease Classification Performance ............................................................... 59 5.4.2 Specific Contribution of Components ................................... 60 5.4.3 Robustness and Generalization .......................................... 61 Conclusion and Perspectives 62
Côte titre :	MAI/0977

Enhancing Deep Learning with Quantum Computing: Exploring Hybrid Algorithms for Image Classification [document électronique] / Sabrina Lazeli ; Abdelouahab Moussaoui, Directeur de thèse . - [S.l.] : Setif:UFA, 2025 . - 1 vol (66 f .) ; 29 cm.
Langues : Anglais (eng)

Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Deep Learning Quantum Computing Image Classification
Index. décimale :	004 Informatique
Résumé :	This thesis explores the integration of quantum computing and deep learning paradigms to enhance image classification, with a particular focus on detecting Alzheimer’s disease stages from MRI images. An innovative hybrid architecture, combining the pre-trained ResNet50 neural network for feature extraction with a variational quantum circuit (VQC) for classification, was developed and evaluated on the Augmented Alzheimer MRI Dataset. This approach leverages the hierarchical feature extraction capabilities of classical convolutional neural networks and quantum properties such as superposition and entanglement to enhance the representation of complex patterns. The results demonstrate an overall accuracy of 97.35%, with outstanding performance in discriminating moderate stages (F1-score of 99.92%) and confirmed robustness through low variance. A comparative analysis with state-of-the-art approaches positions the proposed model among the top performers, highlighting the potential of hybrid quantum-classical algorithms to overcome computational limitations of classical methods, despite the constraints of current Noisy Intermediate-Scale Quantum NISQ devices. This work also proposes perspectives for optimizing quantum circuits and extending this approach to other medical imaging tasks, emphasizing the importance of future advancements in quantum hardware for practical implementation.
Note de contenu :	Sommaire General Introduction 8 0.1 Research problem ................................................................. 9 0.2 Objectives and contributions..................................................... 9 1 Theoretical Foundations of Quantum Computing 11 1.1 Principles of quantum computing ............................................... 12 1.1.1 Qubits and superposition ................................................ 12 1.1.2 Quantum entanglement .................................................. 12 1.1.3 Measurement .............................................................. 13 1.1.4 Quantum gates and circuits.............................................. 13 1.2 NISQ Devices: Noisy Intermediate-Scale Quantum Computing ............... 16 1.2.1 Special features of NISQ devices ........................................ 16 1.2.2 Hardware Architectures of NISQ Devices ............................... 17 1.3 Fundamental Quantum Algorithms ............................................. 18 1.3.1 Grover’s Algorithm ....................................................... 18 1.3.2 Shor’s Algorithm.......................................................... 18 2 Theoretical Foundations of Deep Learning 20 2.1 Principles of Deep learning ...................................................... 20 2.1.1 Artificial Neural Networks (ANN)....................................... 21 2.1.2 Convolutional Neural Networks (CNN) ................................. 21 2.1.3 Recurrent Neural Networks (RNN) ..................................... 23 2.1.4 Generative Adversarial Networks (GANs) .............................. 23 2.1.5 Current Challenges of Classical Deep Learning Approaches ........... 23 3 Hybrid Quantum Classical Algorithms 25 3.1 Structure of hybrid quantum-classical algorithms .............................. 25 3.1.1 Variational quantum circuit (VQC) ..................................... 27 3.1.2 Cost Functions ............................................................ 33 3.1.3 Optimization .............................................................. 34 3.2 Hybrid Quantum Classical Approaches for Image Classification: State of the Art ............................................................................ 35 3.2.1 Quantum Machine Learning for Image Classification introduced by Senokosov et al. ........................................................... 35 3.2.2 COVID-19 Detection Using Quantum Classical Transfer Learning Introduced by E. Acar and I. Yilmaz ................................... 36 3.2.3 Quantum Convolutional Neural Network for Image Classification Introduced by Al-Yousif et Al-Khateeb ................................ 37 3.2.4 Deep Ensemble learning and quantum machine learning approach for Alzheimer’s disease detection Introduced by A. J. Belay ......... 38 3.3 Challenges and Opportunities of Hybrid Quantum Classical Algorithms..... 38 3.3.1 The Challenges ........................................................... 39 3.3.2 The Advantages........................................................... 39 4 Hybrid Model for Image Classification: The Proposed Approach 41 4.1 Alzheimer’s Disease overview .................................................... 41 4.1.1 Symptoms and progression of the disease ............................... 41 4.1.2 Diagnostic methods and challenges of early detection ................. 41 4.1.3 Role of image classification in Alzheimer’s Diagnosis .................. 42 4.2 Hybrid Model Architecture ...................................................... 42 4.2.1 Classic Component: ResNet50........................................... 43 4.2.2 Quantum Component: Variational Quantum Circuit .................. 44 4.2.3 Hybrid Integration and Complete Architecture ........................ 45 4.3 DataSet and Preparation ......................................................... 47 4.3.1 Augmented Alzheimer MRI Dataset .................................... 47 4.3.2 Augmentation and Preprocessing........................................ 49 4.4 Training Configuration and Optimization....................................... 50 4.4.1 Multi-Scale Optimization Strategy ...................................... 50 4.4.2 Training configuration .................................................... 50 4.4.3 Hardware configuration .................................................. 51 4.4.4 Evaluation Metrics ....................................................... 51 5 Results and Analysis 54 5.1 Hybrid model performance ....................................................... 54 5.1.1 Final Results .............................................................. 54 5.2 Convergence Analysis............................................................. 55 5.2.1 Evolution of the Loss Function .......................................... 55 5.2.2 Evolution of the Accuracy Function..................................... 56 5.3 Performance Analysis by Class .................................................. 57 5.4 Validation of Hybrid Architecture ............................................... 59 5.4.1 State of the Art Comparison for Alzheimer’s Disease Classification Performance ............................................................... 59 5.4.2 Specific Contribution of Components ................................... 60 5.4.3 Robustness and Generalization .......................................... 61 Conclusion and Perspectives 62
Côte titre :	MAI/0977