Quantum Machine Learning with HQC Architectures using non-Classically Simulable Feature Maps

Ahmad, Syed Farhan; Rawat, Raghav; Moharir, Minal

doi:10.1109/iccike51210.2021.9410753

Cited by 4 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of a classical SVM is 80%, while the accuracy on the simulator is 70%. On the physical devices, the accuracies in both cases are 69%, though it is important to note that accuracies can vary in some cases on different quantum computers [11]. Although the HQC algorithm did not outperform the classical SVM, the relative closeness demonstrates the potential for HQC machine learning to be successful.…”

Section: Quantum Classificationmentioning

confidence: 95%

“…One example of a quantum classifier is provided by [11]. In this example, a HQC support vector machine (SVM) is implemented to classify whether workers in the tech world will eventually have a mental illness.…”

Section: Quantum Classificationmentioning

confidence: 99%

“…The circuit is measured for a classical result, which is fed to a classical loss function. With these results, the parameters are updated, and the process is repeated [11]. This process highlights the fundamentals of HQC machine learning with PQCs.…”

Section: Quantum Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Survey of NISQ Era Hybrid Quantum-Classical Machine Learning Research

Luca

2021

JAIT

View full text Add to dashboard Cite

Quantum computing is a rapidly growing field that has received a significant amount of support in the past decade in industry and academia. Several physical quantum computers are now freely available to use through cloud services, with some implementations supporting upwards of hundreds of qubits. These advances mark the beginning of the Noisy Intermediate-Scale Quantum (NISQ) era of quantum computing, paving the way for hybrid quantum-classical systems. This work provides an introductory overview of gate-model quantum computing through the Visual IoT/Robotics Programming Language Environment and a survey of recent applications of NISQ era quantum computers to hybrid quantum-classical machine learning.

show abstract

Section: Quantum Classificationmentioning

confidence: 95%

Section: Quantum Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Survey of NISQ Era Hybrid Quantum-Classical Machine Learning Research

Luca

2021

JAIT

View full text Add to dashboard Cite

show abstract

“…2.The input layer where the encoded features via the ZFeatureMap [33], it is a quantum circuit that prepares a quantum state in a way that can be used to encode classical data into a quantum state for processing on a quantum computer. Specifically, the ZFeatureMap is used to encode classical data as rotations around the Z-axis of qubits in a quantum circuit, see figure 4a. 3.Included in the convolution and pooling layer are two unitary matrices with qubit parameters.…”

Section: Quantum Cnnmentioning

confidence: 99%

A New Quantum Circuits of Quantum Convolutional Neural Network for X-Ray Images Classification

Yousif,

Al-Khateeb,

Garcia-Zapirain

2024

IEEE Access

View full text Add to dashboard Cite

A common model for classifying images is the convolutional neural network (CNN), which has the benefit of effectively using data correlation information. Despite their remarkable success, classical CNNs may face challenges in achieving further improvements in accuracy, computational efficiency, explainability, and generalization. However, if the specified data dimension or model grows too large, CNN becomes difficult to train effectively with a slowdown processing. In order to address a problem using CNN utilizing quantum computing, Quantum Convolutional Neural Network (QCNN) proposes a novel quantum solution or enhances the functionality of an existing learning model in terms of processing time during training. This paper presents a comparative analysis between classical Convolutional Neural Networks (CNNs) and a novel quantum circuit architecture tailored for image-based tasks, emphasizing the adaptability and versatility of quantum circuits in enhancing feature extraction capabilities and then final accuracy and processing time. A MNIST and covidx-cxr3 datasets was used to train quantum-CNN models, and the results of these comparisons were made with traditional CNN performance. The results demonstrate that the suggested QCNN beat the traditional CNN in terms of recognition accuracy and processing speed (process time) when combined with cutting-edge feature extraction techniques. This superiority is particularly evident when trained on the covidx-cxr3 dataset, highlighting the potential for quantum computing to revolutionize image classification tasks.

show abstract

Teaching Quantum Machine Learning in Computer Science

Luca

Chen

2023

2023 IEEE 15th International Symposium on Autonomous Decentralized System (ISADS)

View full text Add to dashboard Cite

Quantum Machine Learning with HQC Architectures using non-Classically Simulable Feature Maps

Cited by 4 publications

References 13 publications

Survey of NISQ Era Hybrid Quantum-Classical Machine Learning Research

Survey of NISQ Era Hybrid Quantum-Classical Machine Learning Research

A New Quantum Circuits of Quantum Convolutional Neural Network for X-Ray Images Classification

Teaching Quantum Machine Learning in Computer Science

Contact Info

Product

Resources

About