A Unitary Weights Based One-Iteration Quantum Perceptron Algorithm for Non-Ideal Training Sets

Liu, Wenjie; Gao, Peipei; Wang, Yuxiang; Yu, Wai; Zhang, Maojun

doi:10.1109/access.2019.2896316

Cited by 26 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data dimensions can be increased or reduced according to the increments and decrements in the perceptrons, and they come from the learning of the provided data. Different types of studies and applications were then developed based on the algorithm of perceptrons [45][46][47][48][49].…”

Section: B Multilayer Perceptron Networkmentioning

confidence: 99%

Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine

Chiu

Kuo

2020

IEEE Access

View full text Add to dashboard Cite

Section: B Multilayer Perceptron Networkmentioning

confidence: 99%

Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine

Chiu

Kuo

2020

IEEE Access

View full text Add to dashboard Cite

“…Neto’s perceptron reproduces the step function of the inner product between input and weights and has a memory that can be updated during its own execution. Lastly, Liu et al [ 44 ] presented a quantum perceptron algorithm based on unitary weights, where the singular value decomposition of the total weight matrix from the training dataset is retained in order to convert the weight matrix to be unitary. The model was validated using a number of universal quantum gates within one iteration.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, it is not clear if there is a possibility to perceive whether the neuron output is dependent on the internal state or not. Second is the perceptron described in [ 44 ], which is a one-iteration perceptron algorithm based on unitary weights.…”

Section: Related Workmentioning

confidence: 99%

A Novel Autonomous Perceptron Model for Pattern Classification Applications

Sagheer

Zidan

Abdelsamea

2019

Entropy

View full text Add to dashboard Cite

Pattern classification represents a challenging problem in machine learning and data science research domains, especially when there is a limited availability of training samples. In recent years, artificial neural network (ANN) algorithms have demonstrated astonishing performance when compared to traditional generative and discriminative classification algorithms. However, due to the complexity of classical ANN architectures, ANNs are sometimes incapable of providing efficient solutions when addressing complex distribution problems. Motivated by the mathematical definition of a quantum bit (qubit), we propose a novel autonomous perceptron model (APM) that can solve the problem of the architecture complexity of traditional ANNs. APM is a nonlinear classification model that has a simple and fixed architecture inspired by the computational superposition power of the qubit. The proposed perceptron is able to construct the activation operators autonomously after a limited number of iterations. Several experiments using various datasets are conducted, where all the empirical results show the superiority of the proposed model as a classifier in terms of accuracy and computational time when it is compared with baseline classification models.

show abstract

“…Q UANTUM Machine Learning (QML) is an interdisciplinary field where Quantum Computing (QC) and Machine Learning (ML) converge. Interest in QML over the last couple of years has grown largely due to the advances in hardware implementations of quantum devices known as Noisy Intermediate Scale Quantum (NISQ) devices [1], [2]. The goal of this rising field is to describe learning models that apply the benefits of computing on quantum devices so that operations in machine learning can be performed [3] and potentially improved.…”

Section: Introductionmentioning

confidence: 99%

TensorFlow Quantum: Impacts of Quantum State Preparation on Quantum Machine Learning Performance

2020

View full text Add to dashboard Cite

Learning methodologies on quantum devices have shown that there are advantages in utilizing quantum properties. A requirement for using quantum computing in machine learning techniques is the data representation as quantum states. In Quantum Machine Learning, quantum state preparation is paramount to attain a functional pipeline in a model. One state preparation method, amplitude encoding, allows a dataset to be mapped or encoded more robustly and enhances the learning of quantum models. Albeit more densely represented, a dataset which has been prepared by amplitude encoding provides a more learnable input to a model. The two main advantages from using amplitude encoding are an increase in classification accuracy and reduced variability of learning epoch to epoch. In this paper, we compare the basic implementations of TensorFlow Quantum's Quantum Convolutional Neural Network and a hybrid quantum-classical network using angle encoding, with a third network of our design that utilizes amplitude encoding for enriched state preparation. Our results show there is a direct benefit in performing amplitude encoding before training a TensorFlow Quantum hybrid quantum-classical model. In the best case scenario, amplitude encoding made classifying the samples 8.9% more accurate.

show abstract

A Unitary Weights Based One-Iteration Quantum Perceptron Algorithm for Non-Ideal Training Sets

Cited by 26 publications

References 33 publications

Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine

Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine

A Novel Autonomous Perceptron Model for Pattern Classification Applications

TensorFlow Quantum: Impacts of Quantum State Preparation on Quantum Machine Learning Performance

Contact Info

Product

Resources

About