Ultrafast neuromorphic computing driven by polariton nonlinearities
Abstract Neuromorphic computing offers a promising approach to artificial intelligence by mimicking biological neural networks to perform complex tasks efficiently. While software-based simulations have demonstrated the potential of neuromorphic architectures, a physical platform is crucial to fully...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-06-01
|
| Series: | eLight |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43593-025-00087-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849724873638674432 |
|---|---|
| author | Yusong Gan Ying Shi Sanjib Ghosh Haiyun Liu Huawen Xu Qihua Xiong |
| author_facet | Yusong Gan Ying Shi Sanjib Ghosh Haiyun Liu Huawen Xu Qihua Xiong |
| author_sort | Yusong Gan |
| collection | DOAJ |
| description | Abstract Neuromorphic computing offers a promising approach to artificial intelligence by mimicking biological neural networks to perform complex tasks efficiently. While software-based simulations have demonstrated the potential of neuromorphic architectures, a physical platform is crucial to fully realize its computational advantages. Herein, we present the first demonstration of perovskite microcavity exciton polaritons as a platform for reservoir computing-based artificial neural networks. By leveraging the nonlinear response properties of exciton polaritons, we developed a neuromorphic computing architecture capable of performing classification tasks with single-step training, eliminating the need for iterative algorithms like backpropagation. Applying this system to a handwritten digit recognition task, we achieve 92% classification accuracy at room temperature. Notably, we also show that the system is dynamically nonlinear, further enhancing the potential to improve classification efficiency and address more complex tasks. Our findings advocate the promising capabilities of perovskite exciton polaritons as energy-efficient, ultrafast response platforms for artificial intelligence, paving the way for next-generation computational technologies. |
| format | Article |
| id | doaj-art-a1b901ec006b4527b1a2f8ff08e5db55 |
| institution | DOAJ |
| issn | 2097-1710 2662-8643 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | eLight |
| spelling | doaj-art-a1b901ec006b4527b1a2f8ff08e5db552025-08-20T03:10:38ZengSpringerOpeneLight2097-17102662-86432025-06-01511910.1186/s43593-025-00087-9Ultrafast neuromorphic computing driven by polariton nonlinearitiesYusong Gan0Ying Shi1Sanjib Ghosh2Haiyun Liu3Huawen Xu4Qihua Xiong5State Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua UniversityState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua UniversityBeijing Academy of Quantum Information SciencesBeijing Academy of Quantum Information SciencesBeijing Academy of Quantum Information SciencesState Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics, Tsinghua UniversityAbstract Neuromorphic computing offers a promising approach to artificial intelligence by mimicking biological neural networks to perform complex tasks efficiently. While software-based simulations have demonstrated the potential of neuromorphic architectures, a physical platform is crucial to fully realize its computational advantages. Herein, we present the first demonstration of perovskite microcavity exciton polaritons as a platform for reservoir computing-based artificial neural networks. By leveraging the nonlinear response properties of exciton polaritons, we developed a neuromorphic computing architecture capable of performing classification tasks with single-step training, eliminating the need for iterative algorithms like backpropagation. Applying this system to a handwritten digit recognition task, we achieve 92% classification accuracy at room temperature. Notably, we also show that the system is dynamically nonlinear, further enhancing the potential to improve classification efficiency and address more complex tasks. Our findings advocate the promising capabilities of perovskite exciton polaritons as energy-efficient, ultrafast response platforms for artificial intelligence, paving the way for next-generation computational technologies.https://doi.org/10.1186/s43593-025-00087-9Perovskite microcavityExciton polaritonsNeuromorphic computingDynamical nonlinearImage classification |
| spellingShingle | Yusong Gan Ying Shi Sanjib Ghosh Haiyun Liu Huawen Xu Qihua Xiong Ultrafast neuromorphic computing driven by polariton nonlinearities eLight Perovskite microcavity Exciton polaritons Neuromorphic computing Dynamical nonlinear Image classification |
| title | Ultrafast neuromorphic computing driven by polariton nonlinearities |
| title_full | Ultrafast neuromorphic computing driven by polariton nonlinearities |
| title_fullStr | Ultrafast neuromorphic computing driven by polariton nonlinearities |
| title_full_unstemmed | Ultrafast neuromorphic computing driven by polariton nonlinearities |
| title_short | Ultrafast neuromorphic computing driven by polariton nonlinearities |
| title_sort | ultrafast neuromorphic computing driven by polariton nonlinearities |
| topic | Perovskite microcavity Exciton polaritons Neuromorphic computing Dynamical nonlinear Image classification |
| url | https://doi.org/10.1186/s43593-025-00087-9 |
| work_keys_str_mv | AT yusonggan ultrafastneuromorphiccomputingdrivenbypolaritonnonlinearities AT yingshi ultrafastneuromorphiccomputingdrivenbypolaritonnonlinearities AT sanjibghosh ultrafastneuromorphiccomputingdrivenbypolaritonnonlinearities AT haiyunliu ultrafastneuromorphiccomputingdrivenbypolaritonnonlinearities AT huawenxu ultrafastneuromorphiccomputingdrivenbypolaritonnonlinearities AT qihuaxiong ultrafastneuromorphiccomputingdrivenbypolaritonnonlinearities |