An Evaluation of Hardware-Efficient Quantum Neural Networks for Image Data Classification

Nguyen, Tuan-Anh; Paik, Incheon; Watanobe, Yutaka; Thang, Truong Cong

doi:10.3390/electronics11030437

Cited by 14 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neuromorphic unit described here can be used to assemble complex architectures, in particular, quantum neural networks [32,33]. The output QD register can serve as an input register in the next layer.…”

Section: Neuromorphic Electron Waveguidesmentioning

confidence: 99%

Design of Nanoscale Quantum Interconnects Aided by Conditional Generative Adversarial Networks

Preda,

Pantis-Simut,

Marciu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Interconnecting nanodevices with the aim of assembling quantum computing architectures is one of the current outstanding challenges. At the nanoscale, the quantum interconnects become comparable in complexity with the active devices and should be treated on equal footing. In addition, they can play an active role in the switching properties. Here, we investigate the charge localization in neuromorphic bi-dimensional systems, which serve as quantum interconnects (QIs) between quantum dot registers. We define a device structure where, by manipulating the charging of a floating gate array, one defines the QI potential map, which can host a few interacting electrons. The ground state charge density may be extracted by measuring the tunneling current perpendicular to the device surface, yielding a convoluted image of the electron distribution. Using image-to-image translation methods, we achieve the mapping of the charge density from the confinement potential, as well as by deconvoluting the tunneling current map, which can be obtained by a direct measurement. Thus, we provide a proof-of-concept for a reconfigurable device, which can be used to design quantum many-electron devices.

show abstract

Section: Neuromorphic Electron Waveguidesmentioning

confidence: 99%

Design of Nanoscale Quantum Interconnects Aided by Conditional Generative Adversarial Networks

Preda,

Pantis-Simut,

Marciu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Figure 4 presents the circuit. These quantum layers may be repeated and the repeated layers may be cascaded together to form a more expressive network, which generally performs better [34]. However, these effects on performance still depend on the data and the problem at hand.…”

Section: B Quantum Neural Network (Qnn)mentioning

confidence: 99%

A Robust Hybrid Classical and Quantum Model for Short-Term Wind Speed Forecasting

Hong,

Arce,

Huang

2023

IEEE Access

View full text Add to dashboard Cite

Power scheduling by power utilities is more difficult than in the past decades because of a high penetration of renewable power generation, such as wind power generation, with highly uncertain and stochastic characteristics. To address this issue, a highly accurate technique for forecasting wind speed must be developed. In this work, a hybrid classical-quantum model is developed to exploit the advantages of two powerful models, a long short-term memory (LSTM) and a quantum neural network. Quantum neural networks, also known as parameterized quantum circuits, act like machine learning models but with greater expressive power. They comprise quantum gates that apply the principles of quantum mechanics in order to achieve quantum advantage. Additionally, to obtain a robust design that is insensitive to seasonal changes in the data, the Taguchi method is used to set up orthogonal experiments to set the hyperparameters of the proposed model. Historical data from seven sites in various countries (Taiwan, the Philippines, China, and South Korea) are used to forecast 24-hour-ahead wind speeds at the Fuhai wind farm near Taiwan. Comparative simulation results show that the proposed robust hybrid classical-quantum model outperforms current state-of-art models, such as classical nonlinear autoregressive network, random forest, extreme gradient boosting, support vector regression, and classical LSTM.INDEX TERMS Deep learning model, quantum neural network, robust design, wind speed forecasting

show abstract

“…Deep Learning (DL), as a sub-section of ML, is a concept with the aid of artificial neural networks through advancing learning capabilities in object detection and image recognition. DL approaches have a complex structure as it requires a high volume of training data and high-performance computing resources [8][9][10]. To improve the performance accuracy for the classification of three rice groups, a deep convolutional neural network (DCNN) based structure is proposed with a key focus on minimizing training errors [11].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Classification of Rice Variety with Quantized Neural Networks

Tasci,

Istanbullu,

Kosunalp

et al. 2023

Electronics

View full text Add to dashboard Cite

Rice, as one of the significant grain products across the world, features a wide range of varieties in terms of usability and efficiency. It may be known with various varieties and regional names depending on the specific locations. To specify a particular rice type, different features are considered, such as shape and color. This study uses an available dataset in Turkey consisting of five different varieties: Ipsala, Arborio, Basmati, Jasmine, and Karacadag. The dataset introduces 75,000 grain images in total; each of the 5 varieties has 15,000 samples with a 256 × 256-pixel dimension. The main contribution of this paper is to create Quantized Neural Network (QNN) models to efficiently classify rice varieties with the purpose of reducing resource usage on edge devices. It is well-known that QNN is a successful method for alleviating high computational costs and power requirements in response to many Deep Learning (DL) algorithms. These advantages of the quantization process have the potential to provide an efficient environment for artificial intelligence applications on microcontroller-driven edge devices. For this purpose, we created eight different QNN networks using the MLP and Lenet-5-based deep learning models with varying quantization levels to be trained by the dataset. With the Lenet-5-based QNN network created at the W3A3 quantization level, a 99.87% classification accuracy level was achieved with only 23.1 Kb memory size used for the parameters. In addition to this tremendous benefit of memory usage, the number of billion transactions per second (GOPs) is 23 times less than similar classification studies.

show abstract

An Evaluation of Hardware-Efficient Quantum Neural Networks for Image Data Classification

Cited by 14 publications

References 28 publications

Design of Nanoscale Quantum Interconnects Aided by Conditional Generative Adversarial Networks

Design of Nanoscale Quantum Interconnects Aided by Conditional Generative Adversarial Networks

A Robust Hybrid Classical and Quantum Model for Short-Term Wind Speed Forecasting

An Efficient Classification of Rice Variety with Quantized Neural Networks

Contact Info

Product

Resources

About