Variational Methods in Optical Quantum Machine Learning
The computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum Computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving capabilities while offering a deeper understanding o...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10325513/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207016399831040 |
|---|---|
| author | Marco Simonetti Damiano Perri Osvaldo Gervasi |
| author_facet | Marco Simonetti Damiano Perri Osvaldo Gervasi |
| author_sort | Marco Simonetti |
| collection | DOAJ |
| description | The computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum Computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving capabilities while offering a deeper understanding of complex systems. Our research proposes new variational methods based on a deep learning system based on an optical quantum neural network applied to Machine Learning models for point classification. As a case study, we considered the binary classification of points belonging to a certain geometric pattern (the Two-Moons Classification problem) on a plane. We think it is reasonable to expect benefits from using hybrid deep learning systems (classical + quantum), not just in terms of accelerating computation but also in understanding the underlying phenomena and mechanisms. This will result in the development of new machine-learning paradigms and a significant advancement in the field of quantum computation. The selected dataset is a set of 2D points creating two interleaved semicircles and is based on a 2D binary classification generator, which aids in evaluating the performance of particular methods. The two coordinates of each unique point, <inline-formula> <tex-math notation="LaTeX">$x_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$x_{2}$ </tex-math></inline-formula>, serve as the features since they present two disparate data sets in a two-dimensional representation space. The goal was to create a quantum deep neural network that could recognise and categorise points accurately with the fewest trainable parameters possible. |
| format | Article |
| id | doaj-art-4f3e1872083d4422b1a40dbd93d91017 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-4f3e1872083d4422b1a40dbd93d910172025-02-07T00:00:41ZengIEEEIEEE Access2169-35362023-01-011113139413140810.1109/ACCESS.2023.333562510325513Variational Methods in Optical Quantum Machine LearningMarco Simonetti0https://orcid.org/0000-0003-2923-5519Damiano Perri1https://orcid.org/0000-0001-6815-6659Osvaldo Gervasi2https://orcid.org/0000-0003-4327-520XDepartment of Mathematics and Computer Science, University of Florence, Florence, ItalyDepartment of Mathematics and Computer Science, University of Perugia, Perugia, ItalyDepartment of Mathematics and Computer Science, University of Perugia, Perugia, ItalyThe computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum Computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving capabilities while offering a deeper understanding of complex systems. Our research proposes new variational methods based on a deep learning system based on an optical quantum neural network applied to Machine Learning models for point classification. As a case study, we considered the binary classification of points belonging to a certain geometric pattern (the Two-Moons Classification problem) on a plane. We think it is reasonable to expect benefits from using hybrid deep learning systems (classical + quantum), not just in terms of accelerating computation but also in understanding the underlying phenomena and mechanisms. This will result in the development of new machine-learning paradigms and a significant advancement in the field of quantum computation. The selected dataset is a set of 2D points creating two interleaved semicircles and is based on a 2D binary classification generator, which aids in evaluating the performance of particular methods. The two coordinates of each unique point, <inline-formula> <tex-math notation="LaTeX">$x_{1}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$x_{2}$ </tex-math></inline-formula>, serve as the features since they present two disparate data sets in a two-dimensional representation space. The goal was to create a quantum deep neural network that could recognise and categorise points accurately with the fewest trainable parameters possible.https://ieeexplore.ieee.org/document/10325513/Quantum computingvariational methodsdeep learningquantum feed-forward neural networksoptical quantum computing |
| spellingShingle | Marco Simonetti Damiano Perri Osvaldo Gervasi Variational Methods in Optical Quantum Machine Learning IEEE Access Quantum computing variational methods deep learning quantum feed-forward neural networks optical quantum computing |
| title | Variational Methods in Optical Quantum Machine Learning |
| title_full | Variational Methods in Optical Quantum Machine Learning |
| title_fullStr | Variational Methods in Optical Quantum Machine Learning |
| title_full_unstemmed | Variational Methods in Optical Quantum Machine Learning |
| title_short | Variational Methods in Optical Quantum Machine Learning |
| title_sort | variational methods in optical quantum machine learning |
| topic | Quantum computing variational methods deep learning quantum feed-forward neural networks optical quantum computing |
| url | https://ieeexplore.ieee.org/document/10325513/ |
| work_keys_str_mv | AT marcosimonetti variationalmethodsinopticalquantummachinelearning AT damianoperri variationalmethodsinopticalquantummachinelearning AT osvaldogervasi variationalmethodsinopticalquantummachinelearning |