Comparing concepts of quantum and classical neural network models for image classification task
arXiv:2108.08875 · doi:10.1007/978-3-030-81523-3_6
Abstract
While quantum architectures are still under development, when available, they will only be able to process quantum data when machine learning algorithms can only process numerical data. Therefore, in the issues of classification or regression, it is necessary to simulate and study quantum systems that will transfer the numerical input data to a quantum form and enable quantum computers to use the available methods of machine learning. This material includes the results of experiments on training and performance of a hybrid quantum-classical neural network developed for the problem of classification of handwritten digits from the MNIST data set. The comparative results of two models: classical and quantum neural networks of a similar number of training parameters, indicate that the quantum network, although its simulation is time-consuming, overcomes the classical network (it has better convergence and achieves higher training and testing accuracy).
arXiv comment11 pages, 6 figures. The final publication is available via https://doi.org/10.1007/978-3-030-81523-3_6
References in corpus (7)
- Quantum Computing in the NISQ era and beyond
- A single-atom electron spin qubit in silicon
- Solid state quantum memory using the 31P nuclear spin
- Universality in Quantum Computation
- Realization of reliable solid-state quantum memory for photonic polarization-qubit
- Bose-Einstein condensate as a quantum memory for a photonic polarization qubit
- Charge qubit in van der Waals heterostructures