@mastersthesis {pub4311,
	title = {Exploring and Benchmarking
Quantum-assisted Neural Networks
with Qubit Layers},
	author = {Manuel Rudolph},
	year = {2020},
	month = {March},
	abstract = {The aim of this work is to explore practical implementations of Quantum and
Quantum-assisted Machine Learning algorithms and benchmark potential bene-
fits of utilizing quantum phenomena in Quantum-assisted Neural Networks with
qubit layers.
Two known approaches of generative Quantum Machine Learning algorithms are
revised to demonstrate the encoding capability and sampling benefits of qubits.
As one possible extension of those generative models, the Quantum-assisted Gen-
erator (QaG) is presented which implements a qubit layer coupled to subsequent
classical layers. The QaG provides promising indications that quantum phenom-
ena may enhance performance of a generative neural network.
This work also considers Hamiltonian-based and gate-based implementations of
quantum-assisted Autoencoders. Using an effective hybrid training approach con-
sisting of simultaneous application of conventional backpropagation and black-
box optimization, we show that the Hamiltonian-based Autoencoder is able to
learn the MNIST data set with good generalization properties. Several ap-
proaches to extend the presented quantum-assisted algorithms are proposed to
further investigate potential benefits of utilizing quantum systems in combination
with Artificial Neural Networks.},
	publisher = {University of Heidelberg},
	booktitle = {University of Heidelberg}
}