Optical Full Adder Based on Integrated Diffractive Neural Network
Light has been intensively investigated as a computing medium due to its high-speed propagation and large operation bandwidth. Since the invention of the first laser in 1960, the development of optical computing technologies has presented both challenges and opportunities. Recent advances in artific...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/16/6/681 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839653272907939840 |
|---|---|
| author | Chenchen Deng Yilong Wang Guangpu Li Jiyuan Zheng Yu Liu Chao Wang Yuyan Wang Yuchen Guo Jingtao Fan Qingyang Du Shaoliang Yu |
| author_facet | Chenchen Deng Yilong Wang Guangpu Li Jiyuan Zheng Yu Liu Chao Wang Yuyan Wang Yuchen Guo Jingtao Fan Qingyang Du Shaoliang Yu |
| author_sort | Chenchen Deng |
| collection | DOAJ |
| description | Light has been intensively investigated as a computing medium due to its high-speed propagation and large operation bandwidth. Since the invention of the first laser in 1960, the development of optical computing technologies has presented both challenges and opportunities. Recent advances in artificial intelligence over the past decade have opened up new horizons for optical computing applications. This study presents an end-to-end truth table direct mapping approach using on-chip deep diffractive neural network (D<sup>2</sup>NN) technology to achieve highly parallel optical logic operations. To enable precise logical operations, we propose an on-chip nonlinear solution leveraging the similarity between the hyperbolic tangent (tanh) function and reverse saturable absorption characteristics of quantum dots. We design and demonstrate a 4-bit on-chip D<sup>2</sup>NN full adder circuit. The simulation results show that the proposed architecture achieves 100% accuracy for 4-bit full adders across the entire dataset. |
| format | Article |
| id | doaj-art-12b01401cb8541be9467f83c8b51ef3c |
| institution | Matheson Library |
| issn | 2072-666X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj-art-12b01401cb8541be9467f83c8b51ef3c2025-06-25T14:11:38ZengMDPI AGMicromachines2072-666X2025-06-0116668110.3390/mi16060681Optical Full Adder Based on Integrated Diffractive Neural NetworkChenchen Deng0Yilong Wang1Guangpu Li2Jiyuan Zheng3Yu Liu4Chao Wang5Yuyan Wang6Yuchen Guo7Jingtao Fan8Qingyang Du9Shaoliang Yu10Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, ChinaZhejiang Lab, Hangzhou 311121, ChinaZhejiang Lab, Hangzhou 311121, ChinaLight has been intensively investigated as a computing medium due to its high-speed propagation and large operation bandwidth. Since the invention of the first laser in 1960, the development of optical computing technologies has presented both challenges and opportunities. Recent advances in artificial intelligence over the past decade have opened up new horizons for optical computing applications. This study presents an end-to-end truth table direct mapping approach using on-chip deep diffractive neural network (D<sup>2</sup>NN) technology to achieve highly parallel optical logic operations. To enable precise logical operations, we propose an on-chip nonlinear solution leveraging the similarity between the hyperbolic tangent (tanh) function and reverse saturable absorption characteristics of quantum dots. We design and demonstrate a 4-bit on-chip D<sup>2</sup>NN full adder circuit. The simulation results show that the proposed architecture achieves 100% accuracy for 4-bit full adders across the entire dataset.https://www.mdpi.com/2072-666X/16/6/681optical computingdiffractive neural networklogic computing |
| spellingShingle | Chenchen Deng Yilong Wang Guangpu Li Jiyuan Zheng Yu Liu Chao Wang Yuyan Wang Yuchen Guo Jingtao Fan Qingyang Du Shaoliang Yu Optical Full Adder Based on Integrated Diffractive Neural Network Micromachines optical computing diffractive neural network logic computing |
| title | Optical Full Adder Based on Integrated Diffractive Neural Network |
| title_full | Optical Full Adder Based on Integrated Diffractive Neural Network |
| title_fullStr | Optical Full Adder Based on Integrated Diffractive Neural Network |
| title_full_unstemmed | Optical Full Adder Based on Integrated Diffractive Neural Network |
| title_short | Optical Full Adder Based on Integrated Diffractive Neural Network |
| title_sort | optical full adder based on integrated diffractive neural network |
| topic | optical computing diffractive neural network logic computing |
| url | https://www.mdpi.com/2072-666X/16/6/681 |
| work_keys_str_mv | AT chenchendeng opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT yilongwang opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT guangpuli opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT jiyuanzheng opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT yuliu opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT chaowang opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT yuyanwang opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT yuchenguo opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT jingtaofan opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT qingyangdu opticalfulladderbasedonintegrateddiffractiveneuralnetwork AT shaoliangyu opticalfulladderbasedonintegrateddiffractiveneuralnetwork |