In this work, variational circuits on a continuous-variable (CV) quantum computer are simulated using the PennyLane Framework and used to solve several classic machine learning tasks. Utilizing the CV approach, it is possible to directly encode real numbers into each mode, which is an advantage for more complicated architectures. The necessary background theory in quantum optics and CV quantum computing is presented and used to deduce how neural network inspired architectures can be realized. The parameter shift rule for different gates is deduced and tested with the PennyLane framework. Non-linear 1D regression and 2D function approximation was successfully achieved with a 1 mode and a 2 mode architecture, respectively. Simple classification was performed on the Iris flower dataset to a test-accuracy of 70%. A 1D linear ordinary differential equation was solved using a three mode architecture and a non-linear ordinary differential equation was solved using a 2 mode architecture. Finally, an idea for the practical implementation of a convolutional neural network on a CV quantum computer building on previous results is presented.      «

In this work, variational circuits on a continuous-variable (CV) quantum computer are simulated using the PennyLane Framework and used to solve several classic machine learning tasks. Utilizing the CV approach, it is possible to directly encode real numbers into each mode, which is an advantage for more complicated architectures. The necessary background theory in quantum optics and CV quantum computing is presented and used to deduce how neural network inspired architectures can be realized. Th...     »

In this work, variational circuits on a continuous-variable (CV) quantum computer are simulated using the PennyLane Framework and used to solve several classic machine learning tasks. Utilizing the CV approach, it is possible to directly encode real numbers into each mode, which is an advantage for more complicated architectures. The necessary background theory in quantum optics and CV quantum computing is presented and used to deduce how neural network inspired architectures can be realized. The parameter shift rule for different gates is deduced and tested with the PennyLane framework. Non-linear 1D regression and 2D function approximation was successfully achieved with a 1 mode and a 2 mode architecture, respectively. Simple classification was performed on the Iris flower dataset to a test-accuracy of 70%. A 1D linear ordinary differential equation was solved using a three mode architecture and a non-linear ordinary differential equation was solved using a 2 mode architecture. Finally, an idea for the practical implementation of a convolutional neural network on a CV quantum computer building on previous results is presented.      «

In this work, variational circuits on a continuous-variable (CV) quantum computer are simulated using the PennyLane Framework and used to solve several classic machine learning tasks. Utilizing the CV approach, it is possible to directly encode real numbers into each mode, which is an advantage for more complicated architectures. The necessary background theory in quantum optics and CV quantum computing is presented and used to deduce how neural network inspired architectures can be realized. Th...     »