Quantum Vision Transformers
In this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and image analysis. Building upon the previous work, which uses parametrised quantum...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften
2024-02-01
|
| Series: | Quantum |
| Online Access: | https://quantum-journal.org/papers/q-2024-02-22-1265/pdf/ |
| _version_ | 1797300114385010688 |
|---|---|
| author | El Amine Cherrat Iordanis Kerenidis Natansh Mathur Jonas Landman Martin Strahm Yun Yvonna Li |
| author_facet | El Amine Cherrat Iordanis Kerenidis Natansh Mathur Jonas Landman Martin Strahm Yun Yvonna Li |
| author_sort | El Amine Cherrat |
| collection | DOAJ |
| description | In this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and image analysis. Building upon the previous work, which uses parametrised quantum circuits for data loading and orthogonal neural layers, we introduce three types of quantum transformers for training and inference, including a quantum transformer based on compound matrices, which guarantees a theoretical advantage of the quantum attention mechanism compared to their classical counterpart both in terms of asymptotic run time and the number of model parameters. These quantum architectures can be built using shallow quantum circuits and produce qualitatively different classification models. The three proposed quantum attention layers vary on the spectrum between closely following the classical transformers and exhibiting more quantum characteristics. As building blocks of the quantum transformer, we propose a novel method for loading a matrix as quantum states as well as two new trainable quantum orthogonal layers adaptable to different levels of connectivity and quality of quantum computers. We performed extensive simulations of the quantum transformers on standard medical image datasets that showed competitively, and at times better performance compared to the classical benchmarks, including the best-in-class classical vision transformers. The quantum transformers we trained on these small-scale datasets require fewer parameters compared to standard classical benchmarks. Finally, we implemented our quantum transformers on superconducting quantum computers and obtained encouraging results for up to six qubit experiments. |
| first_indexed | 2024-03-07T23:01:33Z |
| format | Article |
| id | doaj.art-d4e3a02e176243288c2d04413c72ca02 |
| institution | Directory Open Access Journal |
| issn | 2521-327X |
| language | English |
| last_indexed | 2024-03-07T23:01:33Z |
| publishDate | 2024-02-01 |
| publisher | Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften |
| record_format | Article |
| series | Quantum |
| spelling | doaj.art-d4e3a02e176243288c2d04413c72ca022024-02-22T14:24:23ZengVerein zur Förderung des Open Access Publizierens in den QuantenwissenschaftenQuantum2521-327X2024-02-018126510.22331/q-2024-02-22-126510.22331/q-2024-02-22-1265Quantum Vision TransformersEl Amine CherratIordanis KerenidisNatansh MathurJonas LandmanMartin StrahmYun Yvonna LiIn this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and image analysis. Building upon the previous work, which uses parametrised quantum circuits for data loading and orthogonal neural layers, we introduce three types of quantum transformers for training and inference, including a quantum transformer based on compound matrices, which guarantees a theoretical advantage of the quantum attention mechanism compared to their classical counterpart both in terms of asymptotic run time and the number of model parameters. These quantum architectures can be built using shallow quantum circuits and produce qualitatively different classification models. The three proposed quantum attention layers vary on the spectrum between closely following the classical transformers and exhibiting more quantum characteristics. As building blocks of the quantum transformer, we propose a novel method for loading a matrix as quantum states as well as two new trainable quantum orthogonal layers adaptable to different levels of connectivity and quality of quantum computers. We performed extensive simulations of the quantum transformers on standard medical image datasets that showed competitively, and at times better performance compared to the classical benchmarks, including the best-in-class classical vision transformers. The quantum transformers we trained on these small-scale datasets require fewer parameters compared to standard classical benchmarks. Finally, we implemented our quantum transformers on superconducting quantum computers and obtained encouraging results for up to six qubit experiments.https://quantum-journal.org/papers/q-2024-02-22-1265/pdf/ |
| spellingShingle | El Amine Cherrat Iordanis Kerenidis Natansh Mathur Jonas Landman Martin Strahm Yun Yvonna Li Quantum Vision Transformers Quantum |
| title | Quantum Vision Transformers |
| title_full | Quantum Vision Transformers |
| title_fullStr | Quantum Vision Transformers |
| title_full_unstemmed | Quantum Vision Transformers |
| title_short | Quantum Vision Transformers |
| title_sort | quantum vision transformers |
| url | https://quantum-journal.org/papers/q-2024-02-22-1265/pdf/ |
| work_keys_str_mv | AT elaminecherrat quantumvisiontransformers AT iordaniskerenidis quantumvisiontransformers AT natanshmathur quantumvisiontransformers AT jonaslandman quantumvisiontransformers AT martinstrahm quantumvisiontransformers AT yunyvonnali quantumvisiontransformers |