Source code for my master's thesis: "Neural Networks on Continuous-Variable Quantum Computers" using the Pennylane Framework from Xanadu.
Using the Pennylane Continuous-Variable Neural Network, several different machine learning tasks are solved.
- 1D regression
- 2D function evaluation
- Simple classification (Iris dataset)
- Solving a linear ODE
- Solving a non-linear ODE
- A Convolutional neural network is implemented and the transform is compared to the theoretical transform. It has a too high error, to be useful at the moment.
Uses the Python package PennyLane:
Ville Bergholm, Josh Izaac, Maria Schuld, Christian Gogolin, M. Sohaib Alam, Shahnawaz Ahmed, Juan Miguel Arrazola, Carsten Blank, Alain Delgado, Soran Jahangiri, Keri McKiernan, Johannes Jakob Meyer, Zeyue Niu, Antal Száva, and Nathan Killoran. PennyLane: Automatic differentiation of hybrid quantum-classical computations. 2018. arXiv:1811.04968
Available with the Apache 2.0 Licence