Generalization Study of Quantum Neural Network
arXiv:2006.02388
Abstract
Generalization is an important feature of neural network, and there have been many studies on it. Recently, with the development of quantum compu-ting, it brings new opportunities. In this paper, we studied a class of quantum neural network constructed by quantum gate. In this model, we mapped the feature data to a quantum state in Hilbert space firstly, and then implement unitary evolution on it, in the end, we can get the classification result by im-plement measurement on the quantum state. Since all the operations in quan-tum neural networks are unitary, the parameters constitute a hypersphere of Hilbert space. Compared with traditional neural network, the parameter space is flatter. Therefore, it is not easy to fall into local optimum, which means the quantum neural networks have better generalization. In order to validate our proposal, we evaluated our model on three public datasets, the results demonstrated that our model has better generalization than the classical neu-ral network with the same structure.
In light of recent research developments and findings, the authors have identified areas for further refinement in the study and have elected to retract the paper to allow for these improvements
References in corpus (9)
- Supervised learning with quantum enhanced feature spaces
- Quantum machine learning in feature Hilbert spaces
- Quantum generalisation of feedforward neural networks
- Entanglement-Based Machine Learning on a Quantum Computer
- Quantum Neuron: an elementary building block for machine learning on quantum computers
- Quantum perceptron over a field and neural network architecture selection in a quantum computer
- Quantum embeddings for machine learning
- Quantum machine learning for data scientists
- Advances in quantum machine learning