Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback
The human brain can efficiently handle multiple tasks simultaneously, with the structural segregation of brain regions closely linked to their functional specialization. In this paper, we propose and experimentally demonstrate multifunctional photonic reservoir computing (MPRC), inspired by this bio...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10836813/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590416053010432 |
|---|---|
| author | Liyue Zhang Weijie Hong Songsui Li Wei Pan Lianshan Yan Bin Luo Xihua Zou |
| author_facet | Liyue Zhang Weijie Hong Songsui Li Wei Pan Lianshan Yan Bin Luo Xihua Zou |
| author_sort | Liyue Zhang |
| collection | DOAJ |
| description | The human brain can efficiently handle multiple tasks simultaneously, with the structural segregation of brain regions closely linked to their functional specialization. In this paper, we propose and experimentally demonstrate multifunctional photonic reservoir computing (MPRC), inspired by this biological characteristic. The neuron states of the photonic reservoir are divided into distinct sections for different tasks by the designing of input matrix, and only a set of output weight matrix, applicable to all tasks, is ultimately trained. Therefore, MPRC is capable of handling multiple tasks simultaneously with a fixed set of parameters, mitigating the tedious process of hyperparameter optimization. The influence of neuron partition size and operating parameters on MPRC performance is studied systematically. Furthermore, the generalizability of MPRC is validated by performing four different tasks simultaneously. Finally, our results are experimentally demonstrated using semiconductor lasers with a time-delay feedback loop. |
| format | Article |
| id | doaj-art-adcc53b4ae624c5bb26800a4da172bfb |
| institution | Kabale University |
| issn | 1943-0655 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-adcc53b4ae624c5bb26800a4da172bfb2025-01-24T00:00:34ZengIEEEIEEE Photonics Journal1943-06552025-01-011711710.1109/JPHOT.2025.352801910836813Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical FeedbackLiyue Zhang0https://orcid.org/0000-0001-6679-4411Weijie Hong1Songsui Li2https://orcid.org/0000-0003-4675-4062Wei Pan3Lianshan Yan4https://orcid.org/0000-0002-3633-7161Bin Luo5Xihua Zou6https://orcid.org/0000-0002-7240-4229Center for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaCenter for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaCenter for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaCenter for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaCenter for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaCenter for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaCenter for Information Photonics and Communications, Southwest Jiaotong University, Chengdu, ChinaThe human brain can efficiently handle multiple tasks simultaneously, with the structural segregation of brain regions closely linked to their functional specialization. In this paper, we propose and experimentally demonstrate multifunctional photonic reservoir computing (MPRC), inspired by this biological characteristic. The neuron states of the photonic reservoir are divided into distinct sections for different tasks by the designing of input matrix, and only a set of output weight matrix, applicable to all tasks, is ultimately trained. Therefore, MPRC is capable of handling multiple tasks simultaneously with a fixed set of parameters, mitigating the tedious process of hyperparameter optimization. The influence of neuron partition size and operating parameters on MPRC performance is studied systematically. Furthermore, the generalizability of MPRC is validated by performing four different tasks simultaneously. Finally, our results are experimentally demonstrated using semiconductor lasers with a time-delay feedback loop.https://ieeexplore.ieee.org/document/10836813/MPRCreservoir computingsemiconductor laser |
| spellingShingle | Liyue Zhang Weijie Hong Songsui Li Wei Pan Lianshan Yan Bin Luo Xihua Zou Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback IEEE Photonics Journal MPRC reservoir computing semiconductor laser |
| title | Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback |
| title_full | Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback |
| title_fullStr | Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback |
| title_full_unstemmed | Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback |
| title_short | Multifunctional Photonic Reservoir Computing Based on Semiconductor Laser With Optical Feedback |
| title_sort | multifunctional photonic reservoir computing based on semiconductor laser with optical feedback |
| topic | MPRC reservoir computing semiconductor laser |
| url | https://ieeexplore.ieee.org/document/10836813/ |
| work_keys_str_mv | AT liyuezhang multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback AT weijiehong multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback AT songsuili multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback AT weipan multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback AT lianshanyan multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback AT binluo multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback AT xihuazou multifunctionalphotonicreservoircomputingbasedonsemiconductorlaserwithopticalfeedback |