Hybrid Quantum–Classical Neural Networks for Efficient MNIST Binary Image Classification DOI Creative Commons

Deepak Ranga,

Sunil Prajapat, Zahid Akhtar

и другие.

Mathematics, Год журнала: 2024, Номер 12(23), С. 3684 - 3684

Опубликована: Ноя. 24, 2024

Image classification is a fundamental task in deep learning, and recent advances quantum computing have generated significant interest neural networks. Traditionally, Convolutional Neural Networks (CNNs) are employed to extract image features, while Multilayer Perceptrons (MLPs) handle decision making. However, parameterized circuits offer the potential capture complex features define sophisticated boundaries. In this paper, we present novel Hybrid Quantum–Classical Network (H-QNN) for classification, demonstrate its effectiveness using MNIST dataset. Our model combines with classical supervised learning enhance accuracy computational efficiency. study, detail architecture of H-QNN, emphasizing capability feature classification. Experimental results that proposed H-QNN outperforms conventional methods various training scenarios, showcasing high-dimensional tasks. Additionally, explore broader applicability hybrid quantum–classical approaches other domains. findings contribute growing body work machine underscore quantum-enhanced models recognition

Язык: Английский

The real-time data processing framework for blockchain and edge computing DOI
Zhaolong Gao, Yan Wei

Alexandria Engineering Journal, Год журнала: 2025, Номер 120, С. 50 - 61

Опубликована: Фев. 11, 2025

Язык: Английский

Процитировано

1

Quantum Machine Learning: Exploring the Role of Data Encoding Techniques, Challenges, and Future Directions DOI Creative Commons

Deepak Ranga,

Aryan Rana,

Sunil Prajapat

и другие.

Mathematics, Год журнала: 2024, Номер 12(21), С. 3318 - 3318

Опубликована: Окт. 23, 2024

Quantum computing and machine learning (ML) have received significant developments which set the stage for next frontier of creative work usefulness. This paper aims at reviewing various data-encoding techniques in Machine Learning (QML) while highlighting their significance transforming classical data into quantum systems. We analyze basis, amplitude, angle, other high-level encodings depth to demonstrate how strategies affect encoding improvements algorithms. However, they identify major problems with framework QML, including scalability, computational burden, noise. Future directions research outline these challenges, aiming enhance excellence constantly evolving technology setting. review shall enable researcher gain an enhanced understanding it also suggests solutions current limitations this area.

Язык: Английский

Процитировано

7

A blockchain-assisted privacy-preserving signature scheme using quantum teleportation for metaverse environment in Web 3.0 DOI
Sunil Prajapat, Garima Thakur, Pankaj Kumar

и другие.

Future Generation Computer Systems, Год журнала: 2024, Номер 164, С. 107581 - 107581

Опубликована: Ноя. 4, 2024

Язык: Английский

Процитировано

4

A decentralized authentication scheme for smart factory based on blockchain DOI Creative Commons
Zhong Cao,

Xudong Wen,

Shan Ai

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 20, 2024

Язык: Английский

Процитировано

0

Security Analysis and Improvement of Authenticated Key Agreement Protocol for Remote Patient Monitoring IoMT DOI

Deepika Gautam,

Garima Thakur, Mohammad S. Obaidat

и другие.

Опубликована: Окт. 16, 2024

Язык: Английский

Процитировано

0

Blockchain-Assisted Cross-Platform Authentication Protocol with Conditional Traceability for Metaverse Environment in Web 3.0 DOI Creative Commons
Garima Thakur,

Deepika Gautam,

Pankaj Kumar

и другие.

IEEE Open Journal of the Communications Society, Год журнала: 2024, Номер 5, С. 7244 - 7261

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0

Hybrid Quantum–Classical Neural Networks for Efficient MNIST Binary Image Classification DOI Creative Commons

Deepak Ranga,

Sunil Prajapat, Zahid Akhtar

и другие.

Mathematics, Год журнала: 2024, Номер 12(23), С. 3684 - 3684

Опубликована: Ноя. 24, 2024

Image classification is a fundamental task in deep learning, and recent advances quantum computing have generated significant interest neural networks. Traditionally, Convolutional Neural Networks (CNNs) are employed to extract image features, while Multilayer Perceptrons (MLPs) handle decision making. However, parameterized circuits offer the potential capture complex features define sophisticated boundaries. In this paper, we present novel Hybrid Quantum–Classical Network (H-QNN) for classification, demonstrate its effectiveness using MNIST dataset. Our model combines with classical supervised learning enhance accuracy computational efficiency. study, detail architecture of H-QNN, emphasizing capability feature classification. Experimental results that proposed H-QNN outperforms conventional methods various training scenarios, showcasing high-dimensional tasks. Additionally, explore broader applicability hybrid quantum–classical approaches other domains. findings contribute growing body work machine underscore quantum-enhanced models recognition

Язык: Английский

Процитировано

0