Scalable Quantum Neural Networks for Classification

By J. Wu et al

Read the original document by opening this link in a new tab.

Table of Contents

I. Introduction
II. Preliminary
A. Quantum gates
B. Quantum encoding
C. Quantum neural network
III. Scalable Quantum Neural Network
A. Encoding unit
B. Variational quantum layers
C. Optimization
D. Building SQNN in small quantum systems
IV. Evaluation
V. Related works
VI. Conclusion

Summary

Scalable Quantum Neural Networks (SQNN) aim to overcome the limitations of current quantum devices by utilizing multiple small-size quantum devices collaboratively. The SQNN system partitions large classical training instances into smaller segments for processing. Quantum feature extractors extract local features from input data, while a quantum predictor uses these features for prediction. The SQNN system enables scalability and flexibility in handling high-dimensional data, providing a promising approach for quantum machine learning tasks. The paper discusses the encoding unit, variational quantum layers, optimization strategies, and implementation of SQNN in small quantum systems.