Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements
Abstract As the demand for computational performance in artificial intelligence (AI) continues to increase, diffractive deep neural networks (D2NNs), which can perform AI computing at the speed of light by repeated optical modulation with diffractive optical elements (DOEs), are attracting attention...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82791-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544764736929792 |
|---|---|
| author | Ikuo Hoshi Koki Wakunami Yasuyuki Ichihashi Ryutaro Oi |
| author_facet | Ikuo Hoshi Koki Wakunami Yasuyuki Ichihashi Ryutaro Oi |
| author_sort | Ikuo Hoshi |
| collection | DOAJ |
| description | Abstract As the demand for computational performance in artificial intelligence (AI) continues to increase, diffractive deep neural networks (D2NNs), which can perform AI computing at the speed of light by repeated optical modulation with diffractive optical elements (DOEs), are attracting attention. DOEs are varied in terms of fabrication methods and materials, and among them, volume holographic optical elements (vHOEs) have unique features such as high selectivity and multiplex recordability for wavelength and angle. However, when those are used for D2NNs, they suffer from unknown wavefront aberrations compounded by multiple fabrication errors. Here, we propose a training method to adapt the model to be unknown wavefront aberrations and demonstrate a D2NN using vHOEs. As a result, the proposed method improved the classification accuracy by approximately 58 percentage points in the optical experiment, with the model trained to classify handwritten digits. The achievement of this study can be extended to the D2NN that enables the independent modulation of multiple wavelengths owing to their wavelength selectivity and wavelength division multiplex recordability. Therefore, it might be promising for various applications that require multiple wavelengths in parallel optical computing, bioimaging, and optical communication. |
| format | Article |
| id | doaj-art-8fe804322a4d42d48dd407335cdba205 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-8fe804322a4d42d48dd407335cdba2052025-01-12T12:20:04ZengNature PortfolioScientific Reports2045-23222025-01-0115111310.1038/s41598-024-82791-zWavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elementsIkuo Hoshi0Koki Wakunami1Yasuyuki Ichihashi2Ryutaro Oi3Applied Electromagnetic Research Center, National Institute of Information and Communications TechnologyApplied Electromagnetic Research Center, National Institute of Information and Communications TechnologyApplied Electromagnetic Research Center, National Institute of Information and Communications TechnologyApplied Electromagnetic Research Center, National Institute of Information and Communications TechnologyAbstract As the demand for computational performance in artificial intelligence (AI) continues to increase, diffractive deep neural networks (D2NNs), which can perform AI computing at the speed of light by repeated optical modulation with diffractive optical elements (DOEs), are attracting attention. DOEs are varied in terms of fabrication methods and materials, and among them, volume holographic optical elements (vHOEs) have unique features such as high selectivity and multiplex recordability for wavelength and angle. However, when those are used for D2NNs, they suffer from unknown wavefront aberrations compounded by multiple fabrication errors. Here, we propose a training method to adapt the model to be unknown wavefront aberrations and demonstrate a D2NN using vHOEs. As a result, the proposed method improved the classification accuracy by approximately 58 percentage points in the optical experiment, with the model trained to classify handwritten digits. The achievement of this study can be extended to the D2NN that enables the independent modulation of multiple wavelengths owing to their wavelength selectivity and wavelength division multiplex recordability. Therefore, it might be promising for various applications that require multiple wavelengths in parallel optical computing, bioimaging, and optical communication.https://doi.org/10.1038/s41598-024-82791-zDiffractive deep neural networkHolographic optical elementMachine learningAdaptive optics |
| spellingShingle | Ikuo Hoshi Koki Wakunami Yasuyuki Ichihashi Ryutaro Oi Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements Scientific Reports Diffractive deep neural network Holographic optical element Machine learning Adaptive optics |
| title | Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements |
| title_full | Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements |
| title_fullStr | Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements |
| title_full_unstemmed | Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements |
| title_short | Wavefront-aberration-tolerant diffractive deep neural networks using volume holographic optical elements |
| title_sort | wavefront aberration tolerant diffractive deep neural networks using volume holographic optical elements |
| topic | Diffractive deep neural network Holographic optical element Machine learning Adaptive optics |
| url | https://doi.org/10.1038/s41598-024-82791-z |
| work_keys_str_mv | AT ikuohoshi wavefrontaberrationtolerantdiffractivedeepneuralnetworksusingvolumeholographicopticalelements AT kokiwakunami wavefrontaberrationtolerantdiffractivedeepneuralnetworksusingvolumeholographicopticalelements AT yasuyukiichihashi wavefrontaberrationtolerantdiffractivedeepneuralnetworksusingvolumeholographicopticalelements AT ryutarooi wavefrontaberrationtolerantdiffractivedeepneuralnetworksusingvolumeholographicopticalelements |