Scholarlink

<p>Classification is a central task in deep learning algorithms. Usually, images are first captured and then processed by a sequence of operations, of which the artificial neuron represents one of the fundamental units. This paradigm requires significant resources that scale (at least) linearly in the image resolution, both in terms of photons and computational operations. Here, we present a quantum optical pattern recognition method for binary classification tasks. It classifies objects without reconstructing their images, using the rate of two-photon coincidences at the output of a Hong-Ou-Mandel interferometer, where both the input and the classifier parameters are encoded into single-photon states. Our method exhibits the behaviour of a classical neuron of unit depth. Once trained, it shows a constant <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="42005_2025_2020_Article_IEq1.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="36" /> </InlineMediaObject> <EquationSource Format="TEX">\({{\mathcal{O}}}(1)\)</EquationSource> <EquationSource Format="MATHML"><math> <mi class="MJX-tex-caligraphic" mathvariant="script">O</mi> <mrow> <mo>(</mo> <mrow> <mn>1</mn> </mrow> <mo>)</mo> </mrow> </math></EquationSource> </InlineEquation> complexity in the number of computational operations and photons required by a single classification. This is a superexponential advantage over a classical artificial neuron.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Quantum optical classifier with superexponential speedup

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月10日

查看全文
  • Simone Roncallo,
  • Angela Rosy Morgillo,
  • Chiara Macchiavello,
  • Lorenzo Maccone,
  • Seth Lloyd

摘要

Classification is a central task in deep learning algorithms. Usually, images are first captured and then processed by a sequence of operations, of which the artificial neuron represents one of the fundamental units. This paradigm requires significant resources that scale (at least) linearly in the image resolution, both in terms of photons and computational operations. Here, we present a quantum optical pattern recognition method for binary classification tasks. It classifies objects without reconstructing their images, using the rate of two-photon coincidences at the output of a Hong-Ou-Mandel interferometer, where both the input and the classifier parameters are encoded into single-photon states. Our method exhibits the behaviour of a classical neuron of unit depth. Once trained, it shows a constant \({{\mathcal{O}}}(1)\) O ( 1 ) complexity in the number of computational operations and photons required by a single classification. This is a superexponential advantage over a classical artificial neuron.