4.7 Article

Quantum generalisation of feedforward neural networks

期刊

NPJ QUANTUM INFORMATION
卷 3, 期 -, 页码 -

出版社

NATURE PORTFOLIO
DOI: 10.1038/s41534-017-0032-4

关键词

-

资金

  1. EU Collaborative Project TherMiQ [618074]
  2. London Institute for Mathematical Sciences
  3. Royal Society
  4. Leverhulme Trust [RPG-2014-055]
  5. UK EPSRC [EP/K034480/1]

向作者/读者索取更多资源

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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据