Transfer learning in hybrid classical-quantum neural networks
We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in whi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften
2020-10-01
|
| Series: | Quantum |
| Online Access: | https://quantum-journal.org/papers/q-2020-10-09-340/pdf/ |
| _version_ | 1818539005731405824 |
|---|---|
| author | Andrea Mari Thomas R. Bromley Josh Izaac Maria Schuld Nathan Killoran |
| author_facet | Andrea Mari Thomas R. Bromley Josh Izaac Maria Schuld Nathan Killoran |
| author_sort | Andrea Mari |
| collection | DOAJ |
| description | We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti. |
| first_indexed | 2024-12-11T21:36:21Z |
| format | Article |
| id | doaj.art-0583ea2281974f6297d7a90366f0db43 |
| institution | Directory Open Access Journal |
| issn | 2521-327X |
| language | English |
| last_indexed | 2024-12-11T21:36:21Z |
| publishDate | 2020-10-01 |
| publisher | Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften |
| record_format | Article |
| series | Quantum |
| spelling | doaj.art-0583ea2281974f6297d7a90366f0db432022-12-22T00:49:59ZengVerein zur Förderung des Open Access Publizierens in den QuantenwissenschaftenQuantum2521-327X2020-10-01434010.22331/q-2020-10-09-34010.22331/q-2020-10-09-340Transfer learning in hybrid classical-quantum neural networksAndrea MariThomas R. BromleyJosh IzaacMaria SchuldNathan KilloranWe extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti.https://quantum-journal.org/papers/q-2020-10-09-340/pdf/ |
| spellingShingle | Andrea Mari Thomas R. Bromley Josh Izaac Maria Schuld Nathan Killoran Transfer learning in hybrid classical-quantum neural networks Quantum |
| title | Transfer learning in hybrid classical-quantum neural networks |
| title_full | Transfer learning in hybrid classical-quantum neural networks |
| title_fullStr | Transfer learning in hybrid classical-quantum neural networks |
| title_full_unstemmed | Transfer learning in hybrid classical-quantum neural networks |
| title_short | Transfer learning in hybrid classical-quantum neural networks |
| title_sort | transfer learning in hybrid classical quantum neural networks |
| url | https://quantum-journal.org/papers/q-2020-10-09-340/pdf/ |
| work_keys_str_mv | AT andreamari transferlearninginhybridclassicalquantumneuralnetworks AT thomasrbromley transferlearninginhybridclassicalquantumneuralnetworks AT joshizaac transferlearninginhybridclassicalquantumneuralnetworks AT mariaschuld transferlearninginhybridclassicalquantumneuralnetworks AT nathankilloran transferlearninginhybridclassicalquantumneuralnetworks |