Defining Quantum Neural Networks via Quantum Time Evolution
This work addresses the computational expense of classical neural networks by offering a more foundational QNN approach, potentially benefiting quantum computing researchers, though it appears incremental in the context of existing QNN research.
The authors tackled the problem of defining and training quantum neural networks (QNNs) by proposing a fundamental algorithm based on quantum time evolution and the Hamiltonian, which is applicable across quantum computing models, and validated it with a quantum backpropagation algorithm on the MNIST dataset in simulation.
This work presents a novel fundamental algorithm for for defining and training Neural Networks in Quantum Information based on time evolution and the Hamiltonian. Classical Neural Network algorithms (ANN) are computationally expensive. For example, in image classification, representing an image pixel by pixel using classical information requires an enormous amount of computational memory resources. Hence, exploring methods to represent images in a different paradigm of information is important. Quantum Neural Networks (QNNs) have been explored for over 20 years. The current forefront work based on Variational Quantum Circuits is specifically defined for the Continuous Variable (CV) Model of quantum computers. In this work, a model is proposed which is defined at a more fundamental level and hence can be inherited by any variants of quantum computing models. This work also presents a quantum backpropagation algorithm to train our QNN model and validate this algorithm on the MNIST dataset on a quantum computer simulation.