Imperial College London
Portrait Picture

Professor Myungshik Kim

Faculty of Natural Sciences, Department of Physics

Chair in Theoretical Quantum Information Sciences
 
 
 
//

Contact

 

+44 (0)20 7594 7754m.kim

 
 
//

Location

 

1202Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Wan:2017:10.1038/s41534-017-0032-4,
author = {Wan, KH and Dahlsten, O and Kristjansson, H and Gardner, R and Kim, MS},
doi = {10.1038/s41534-017-0032-4},
journal = {npj Quantum Information},
title = {Quantum generalisation of feedforward neural networks},
url = {http://dx.doi.org/10.1038/s41534-017-0032-4},
volume = {3},
year = {2017}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.
AU  - Wan,KH
AU  - Dahlsten,O
AU  - Kristjansson,H
AU  - Gardner,R
AU  - Kim,MS
DO  - 10.1038/s41534-017-0032-4
PY  - 2017///
SN  - 2056-6387
TI  - Quantum generalisation of feedforward neural networks
T2  - npj Quantum Information
UR  - http://dx.doi.org/10.1038/s41534-017-0032-4
UR  - http://hdl.handle.net/10044/1/50114
VL  - 3
ER  -
Download