Quantum generalisation of feedforward neural networks

TL;DR

This paper introduces a quantum version of classical feedforward neural networks, enabling efficient training for quantum tasks like state compression and communication protocol discovery, with potential for photon-based implementation.

Contribution

It presents a theoretical framework for quantum neural networks that are reversible and unitary, extending classical neural network concepts into the quantum domain.

Findings

Successfully demonstrated quantum autoencoder for state compression

Discovered quantum communication protocols such as teleportation

Framework is implementation-independent and photon-compatible

Abstract

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.