Quantum classification algorithm with multi-class parallel training

Zhang, Anqi; He, Xiaoyun; Zhao, Shengmei

doi:10.1007/s11128-022-03700-9

Cited by 2 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each test point in these datasets, we evaluate the predicted vector classically using Equation (13). To do this, we evaluate each 𝛼 i = ∑ m|y m =i w m |⟨x|x m ⟩| 2 directly as 𝛼 i = ∑ m|y m =i w m k(x, x m ).…”

Section: Resultsmentioning

confidence: 99%

“…Some of the recent work in quantum machine learning has seen the development of multi-class quantum and quantuminspired classifiers that avoid these heuristic strategies. [9][10][11][12][13][14][15][16] Most recently, the quantum-inspired methods [15,16] use techniques from quantum state discrimination for multi-class classification. Other work has seen the development of quantum convolutional neural networks (QCNNs) for multi-class classification.…”

Section: Introductionmentioning

confidence: 99%

“…In some approaches, these regions are centred around label states; a set of quantum states corresponding to the set of classes. [11,13] In other approaches, these regions or clusters are constructed, through training, to be as far apart as possible in Hilbert space. [10] In both these approaches, the choice of label states is inherently tied to the data encoding strategy and vice versa.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Multi‐Class Quantum Kernel‐Based Classifier

Pillay,

Sinayskiy,

Jembere

et al. 2023

Adv Quantum Tech

View full text Add to dashboard Cite

Multi‐class classification problems are fundamental in many varied domains in research and industry. A popular strategy for solving multi‐class classification problems involves first transforming the problem into many binary classification problems. However, this requires the number of binary classification models that need to be developed to grow with the number of classes. Recent work in quantum machine learning has seen the development of multi‐class quantum classifiers that circumvent this growth by learning a mapping between the data and a set of label states. This work presents the first multi‐class SWAP‐Test classifier inspired by its binary predecessor and the use of label states in recent work. With this classifier, the cost of developing multiple models is avoided. In contrast to previous work, the number of qubits required, the measurement strategy, and the topology of the circuits used is invariant to the number of classes. In addition, unlike other architectures for multi‐class quantum classifiers, the state reconstruction of a single qubit yields sufficient information for multi‐class classification tasks. Both analytical results and numerical simulations show that this classifier is not only effective when applied to diverse classification problems but also robust to certain conditions of noise.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Multi‐Class Quantum Kernel‐Based Classifier

Pillay,

Sinayskiy,

Jembere

et al. 2023

Adv Quantum Tech

View full text Add to dashboard Cite

show abstract

“…Parameterized quantum circuits (PQCs) offer a useful way to implement quantum algorithms [1][2][3][4][5][6][7][8][9][10] and can demonstrate quantum supremacy in the noisy intermediate scale quantum (NISQ) area. [11][12][13][14][15] PQCs are typically composed of fixed gates, e.g., controlled NOTs, or adjustable gates with phase rotations.…”

Section: Introductionmentioning

confidence: 99%

Gray code based gradient-free optimization algorithm for parameterized quantum circuit

Zhang 张,

Wu 武,

Zhao 赵

2024

Chinese Phys. B

View full text Add to dashboard Cite

A Gray code based gradient-free optimization algorithm(GCO) is proposed to update the parameters of parameterized quantum circuits(PQCs) in the paper. Here, each parameter of PQCs is encoded as a binary string, named genes, and a genetic-based method is adopted to select the offsprings. The individuals in the offspring are decoded in Gray code way to keep Hamming distance, and then are evaluated to obtain the best one with the lowest cost value in each iteration. The algorithm is performed iteratively for all parameters one by one until the cost value satisfies the stop condition or the number of iterations is reached. The GCO algorithm is demonstrated for classification tasks in Iris and MNIST datasets, and their performance are compared by those with the Bayesian optimization(BO) algorithm and Binary code based optimization(BCO) algorithm. The simulation results show that the GCO algorithm can reach high accuracies steadily for quantum classification tasks. Importantly, the GCO algorithm has a robust performance in the noise environment.

show abstract

Quantum classification algorithm with multi-class parallel training

Cited by 2 publications

References 28 publications

A Multi‐Class Quantum Kernel‐Based Classifier

A Multi‐Class Quantum Kernel‐Based Classifier

Gray code based gradient-free optimization algorithm for parameterized quantum circuit

Contact Info

Product

Resources

About