FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793310412> ?p ?o ?g. }

• W2793310412 endingPage "109" @default.
• W2793310412 startingPage "99" @default.
• W2793310412 abstract "Google’s AlphaGo represents the impressive performance of deep learning and the backbone of deep learning is the workhorse of highly versatile neural networks. Each network is made up of layers of interconnected neurons and the nonlinear activation function inside each neuron is one of the key factors that account for the unprecedented achievement of deep learning. Learning how to create quantum neural networks has been a long time pursuit since 1990’s from many researchers, unfortunately without much success. The main challenge is to know how to design a nonlinear activation function inside the quantum neuron, because the laws in quantum mechanics require the operations on quantum neurons be unitary and linear. A recent discovery uses a special quantum circuit technique called repeat-until-success to make a nonlinear activation function inside a quantum neuron, which is the hard part of creating this neuron. However, the activation function used in that work is based on the periodic tangent function. Because of this periodicity, the input to this function has to be restricted to the range of [0, π/2), which is a serious constraint for its applications in real world problems. The function’s periodicity also makes its neurons not suited for being trained with gradient descent as its derivatives oscillate. The purpose of our study is to propose a new nonlinear activation function that is not periodic so it can take any real numbers and its neurons can be trained with efficient gradient descent. Our quantum neuron offers the full benefit as a quantum entity to support superposition, entanglement, interference, while also enjoys the full benefit as a classical entity to take any real numbers as its input and can be trained with gradient descent. The performance of the quantum neurons with our new activation function is analyzed on IBM’s 5Q quantum computer and IBM’s quantum simulator." @default.
• W2793310412 created "2018-03-29" @default.
• W2793310412 creator A5050221970 @default.
• W2793310412 date "2018-01-01" @default.
• W2793310412 modified "2023-10-10" @default.
• W2793310412 title "Towards a Real Quantum Neuron" @default.
• W2793310412 cites W1480910789 @default.
• W2793310412 cites W1990514347 @default.
• W2793310412 cites W1992716633 @default.
• W2793310412 cites W1995341919 @default.
• W2793310412 cites W2019101955 @default.
• W2793310412 cites W2044799191 @default.
• W2793310412 cites W2084019889 @default.
• W2793310412 cites W2159566537 @default.
• W2793310412 cites W2560386163 @default.
• W2793310412 cites W2789255422 @default.
• W2793310412 cites W2793680557 @default.
• W2793310412 doi "https://doi.org/10.4236/ns.2018.103011" @default.
• W2793310412 hasPublicationYear "2018" @default.
• W2793310412 type Work @default.
• W2793310412 sameAs 2793310412 @default.
• W2793310412 citedByCount "19" @default.
• W2793310412 countsByYear W27933104122018 @default.
• W2793310412 countsByYear W27933104122019 @default.
• W2793310412 countsByYear W27933104122020 @default.
• W2793310412 countsByYear W27933104122021 @default.
• W2793310412 countsByYear W27933104122022 @default.
• W2793310412 countsByYear W27933104122023 @default.
• W2793310412 crossrefType "journal-article" @default.
• W2793310412 hasAuthorship W2793310412A5050221970 @default.
• W2793310412 hasBestOaLocation W27933104121 @default.
• W2793310412 hasConcept C121332964 @default.
• W2793310412 hasConcept C144133560 @default.
• W2793310412 hasConcept C15744967 @default.
• W2793310412 hasConcept C169760540 @default.
• W2793310412 hasConcept C2778794669 @default.
• W2793310412 hasConcept C41008148 @default.
• W2793310412 hasConcept C62520636 @default.
• W2793310412 hasConcept C84114770 @default.
• W2793310412 hasConceptScore W2793310412C121332964 @default.
• W2793310412 hasConceptScore W2793310412C144133560 @default.
• W2793310412 hasConceptScore W2793310412C15744967 @default.
• W2793310412 hasConceptScore W2793310412C169760540 @default.
• W2793310412 hasConceptScore W2793310412C2778794669 @default.
• W2793310412 hasConceptScore W2793310412C41008148 @default.
• W2793310412 hasConceptScore W2793310412C62520636 @default.
• W2793310412 hasConceptScore W2793310412C84114770 @default.
• W2793310412 hasIssue "03" @default.
• W2793310412 hasLocation W27933104121 @default.
• W2793310412 hasOpenAccess W2793310412 @default.
• W2793310412 hasPrimaryLocation W27933104121 @default.
• W2793310412 hasRelatedWork W1975516339 @default.
• W2793310412 hasRelatedWork W1984247723 @default.
• W2793310412 hasRelatedWork W2023349124 @default.
• W2793310412 hasRelatedWork W2056111390 @default.
• W2793310412 hasRelatedWork W2080652953 @default.
• W2793310412 hasRelatedWork W2159558501 @default.
• W2793310412 hasRelatedWork W2417834905 @default.
• W2793310412 hasRelatedWork W2748952813 @default.
• W2793310412 hasRelatedWork W2782882015 @default.
• W2793310412 hasRelatedWork W2899084033 @default.
• W2793310412 hasVolume "10" @default.
• W2793310412 isParatext "false" @default.
• W2793310412 isRetracted "false" @default.
• W2793310412 magId "2793310412" @default.
• W2793310412 workType "article" @default.