Hybrid classical-quantum autoencoder for anomaly detection

Sakhnenko, Alona; O'Meara, Corey; Ghosh, Kumar; Mendl, Christian B.; Cortiana, Giorgio; Bernabé-Moreno, Juan

doi:10.1007/s42484-022-00075-z

Cited by 10 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for AD, we also noticed that few recent works were devoted to using quantum circuits for AD. Concretely, Gunhee Park et al [ 36 ] proposed a variational quantum one-class classifier; Alona Sakhnenko et al [ 37 ] proposed a hybrid classical-quantum autoencoder for anomaly detection in tabular data. Nevertheless, to the best of our knowledge, no QML work has delved into deep image AD, despite its importance.…”

Section: Related Workmentioning

confidence: 99%

A Quantum-Classical Hybrid Solution for Deep Anomaly Detection

Wang

Huang

Liu

et al. 2023

Entropy

View full text Add to dashboard Cite

Machine learning (ML) has achieved remarkable success in a wide range of applications. In recent ML research, deep anomaly detection (AD) has been a hot topic with the aim of discriminating among anomalous data with deep neural networks (DNNs). Notably, image AD is one of the most representative tasks in current deep AD research. ML’s interaction with quantum computing is giving rise to a heated topic named quantum machine learning (QML), which enjoys great prospects according to recent academic research. This paper attempts to address the image AD problem in a deep manner with a novel QML solution. Specifically, we design a quantum-classical hybrid DNN (QHDNN) that aims to learn directly from normal raw images to train a normality model and then exclude images that do not conform to this model as anomalies during its inference. To enable the QHDNN to perform satisfactorily in deep image AD, we explore multiple quantum layer architectures and design a VQC-based QHDNN solution. Extensive experiments were conducted on commonly used benchmarks to test the proposed QML solution, whose results demonstrate the feasibility of addressing deep image AD with QML. Importantly, the experimental results show that our quantum-classical hybrid solution can even yield superior performance to that of its classical counterpart when they share the same number of learnable parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

A Quantum-Classical Hybrid Solution for Deep Anomaly Detection

Wang

Huang

Liu

et al. 2023

Entropy

View full text Add to dashboard Cite

show abstract

“…The synthetic dataset is utilized in this work for traditional data categorization problems. The authors of [24] suggested a Hybrid classical-quantum Autoencoder (HAE) model with four datasets for monitoring gas power stations. The anomaly is detected and the performance is evaluated here.…”

Section: Related Workmentioning

confidence: 99%

“…In this work, the proposed QC-CNN and existing models such as Quantum Generative Adversarial Network (QGAN) [23], Hybrid classical-quantum Autoencoder (HAE) model [24], Quantum-assisted Neural Networks (QANN) [25], Quantum orthogonal neural network (QONN) [25] are compared. The dataset and application used in these existing models are different from the proposed work.…”

Section: Accuracy Comparison Of the Proposed Model With Quantum Modelsmentioning

confidence: 99%

“…The authors of [23] proposed a QGAN model for a human-centered paradigm that is implemented in the cloud for the synthetic dataset. The authors of [24] suggested an HAE approach as well as four datasets to monitor gas power stations. For medical image classification, two models, QONN and QANN, were proposed in [25].…”

Section: Accuracy Comparison Of the Proposed Model With Quantum Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Quantum Computing Based Neural Networks for Anomaly Classification in燫eal-Time Surveillance Videos

Arafath¹,

Kumar²

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

For intelligent surveillance videos, anomaly detection is extremely important. Deep learning algorithms have been popular for evaluating realtime surveillance recordings, like traffic accidents, and criminal or unlawful incidents such as suicide attempts. Nevertheless, Deep learning methods for classification, like convolutional neural networks, necessitate a lot of computing power. Quantum computing is a branch of technology that solves abnormal and complex problems using quantum mechanics. As a result, the focus of this research is on developing a hybrid quantum computing model which is based on deep learning. This research develops a Quantum Computing-based Convolutional Neural Network (QC-CNN) to extract features and classify anomalies from surveillance footage. A Quantum-based Circuit, such as the real amplitude circuit, is utilized to improve the performance of the model. As far as my research, this is the first work to employ quantum deep learning techniques to classify anomalous events in video surveillance applications. There are 13 anomalies classified from the UCF-crime dataset. Based on experimental results, the proposed model is capable of efficiently classifying data concerning confusion matrix, Receiver Operating Characteristic (ROC), accuracy, Area Under Curve (AUC), precision, recall as well as F1-score. The proposed QC-CNN has attained the best accuracy of 95.65 percent which is 5.37% greater when compared to other existing models. To measure the efficiency of the proposed work, QC-CNN is also evaluated with classical and quantum models.

show abstract

“…These techniques can be implemented on classical as well as quantum computers 10 which makes them even more powerful specially for problems which are unsolvable by any conventional means. There are extensive ongoing efforts on the application of quantum computing in the areas of machine learning [11][12][13] , finance 14 , quantum chemistry 15,16 , drug design and molecular modeling 17 , power systems 18,19 , metrology 20 , to name a few applications. Quantum-enabled methods are the next natural step of the AI studies to support faster computation and more accurate decision making, creating the interdisciplinary field of quantum artificial intelligence 21 .…”

Section: Introductionmentioning

confidence: 99%