Quantum generalisation of feedforward neural networks

K. Wan, O. Dahlsten, H. Kristjansson, R. Gardner, M. Kim

Nature Quantum Information 3, 36 (2017)

#quantumtheory#neuralnetworks#machinelearning

LQ placeholderWe generalise neural networks into a quantum framework, demonstrating the possibility of quantum auto-encoders and teleportation.

We generalise neural networks into a quantum framework, demonstrating the possibility of quantum auto-encoders and teleportation.

We propose a quantum generalisation of a classical neural network. The classical neurons are firstly rendered reversible by adding ancillary bits. Then they are generalised to being quantum reversible, i.e. unitary. (The classical networks we generalise are called feedforward, and have step-function activation functions.) The quantum network can be trained efficiently using gradient descent on a cost function to perform quantum generalisations of classical tasks. We demonstrate numerically that it can: (i) compress quantum states onto a minimal number of qubits, creating a quantum autoencoder, and (ii) discover quantum communication protocols such as teleportation. Our general recipe is theoretical and implementation-independent. The quantum neuron module can naturally be implemented photonically.

Download the PDF

LQ placeholder

Quantum generalisation of feedforward neural networks

K. Wan, O. Dahlsten, H. Kristjansson, R. Gardner, M. Kim

Nature Quantum Information

1 / 121 papers

Contribute to the future!

The London Institute is different. We’re fully dedicated to curiosity-driven research, which has shaped our present and will shape our future. But this focus comes at a cost. Unlike universities, we don’t receive student fees or subsidies, but rely entirely on grants and donations.