Hardware optimization for photonic time-delay reservoir computer dynamics
Reservoir computing (RC) is one kind of neuromorphic computing mainly applied to process sequential data such as time-dependent signals. In this paper, the bifurcation diagram of a photonic time-delay RC system is thoroughly studied, and a method of bifurcation dynamics guided hardware hyperparamete...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Neuromorphic Computing and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2634-4386/acb8d7 |
| _version_ | 1797674777145507840 |
|---|---|
| author | Meng Zhang Zhizhuo Liang Z Rena Huang |
| author_facet | Meng Zhang Zhizhuo Liang Z Rena Huang |
| author_sort | Meng Zhang |
| collection | DOAJ |
| description | Reservoir computing (RC) is one kind of neuromorphic computing mainly applied to process sequential data such as time-dependent signals. In this paper, the bifurcation diagram of a photonic time-delay RC system is thoroughly studied, and a method of bifurcation dynamics guided hardware hyperparameter optimization is presented. The time-evolution equation expressed by the photonic hardware parameters is established while the intrinsic dynamics of the photonic RC system is quantitively studied. Bifurcation dynamics based hyperparameter optimization offers a simple yet effective approach in hardware setting optimization that aims to reduce the complexity and time in hardware adjustment. Three benchmark tasks, nonlinear channel equalization (NCE), nonlinear auto regressive moving average with 10th order time lag (NARMA10) and Santa Fe laser time-series prediction tasks are implemented on the photonic delay-line RC using bifurcation dynamics guided hardware optimization. The experimental results of these benchmark tasks achieved overall good agreement with the simulated bifurcation dynamics modeling results. |
| first_indexed | 2024-03-11T22:05:01Z |
| format | Article |
| id | doaj.art-95793440c2784e4e96c11d556ebc7716 |
| institution | Directory Open Access Journal |
| issn | 2634-4386 |
| language | English |
| last_indexed | 2024-03-11T22:05:01Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Neuromorphic Computing and Engineering |
| spelling | doaj.art-95793440c2784e4e96c11d556ebc77162023-09-25T09:10:20ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862023-01-013101400810.1088/2634-4386/acb8d7Hardware optimization for photonic time-delay reservoir computer dynamicsMeng Zhang0https://orcid.org/0000-0001-7182-8110Zhizhuo Liang1https://orcid.org/0000-0002-7023-1619Z Rena Huang2https://orcid.org/0000-0002-0667-903XDepartment of Electrical Computer and System Engineering, Rensselaer Polytechnic Institute , Troy, NY 12180, United States of AmericaDepartment of Electrical Computer and System Engineering, Rensselaer Polytechnic Institute , Troy, NY 12180, United States of AmericaDepartment of Electrical Computer and System Engineering, Rensselaer Polytechnic Institute , Troy, NY 12180, United States of AmericaReservoir computing (RC) is one kind of neuromorphic computing mainly applied to process sequential data such as time-dependent signals. In this paper, the bifurcation diagram of a photonic time-delay RC system is thoroughly studied, and a method of bifurcation dynamics guided hardware hyperparameter optimization is presented. The time-evolution equation expressed by the photonic hardware parameters is established while the intrinsic dynamics of the photonic RC system is quantitively studied. Bifurcation dynamics based hyperparameter optimization offers a simple yet effective approach in hardware setting optimization that aims to reduce the complexity and time in hardware adjustment. Three benchmark tasks, nonlinear channel equalization (NCE), nonlinear auto regressive moving average with 10th order time lag (NARMA10) and Santa Fe laser time-series prediction tasks are implemented on the photonic delay-line RC using bifurcation dynamics guided hardware optimization. The experimental results of these benchmark tasks achieved overall good agreement with the simulated bifurcation dynamics modeling results.https://doi.org/10.1088/2634-4386/acb8d7photonic time-delay reservoir computingbifurcation dynamicshyperparameter optimization |
| spellingShingle | Meng Zhang Zhizhuo Liang Z Rena Huang Hardware optimization for photonic time-delay reservoir computer dynamics Neuromorphic Computing and Engineering photonic time-delay reservoir computing bifurcation dynamics hyperparameter optimization |
| title | Hardware optimization for photonic time-delay reservoir computer dynamics |
| title_full | Hardware optimization for photonic time-delay reservoir computer dynamics |
| title_fullStr | Hardware optimization for photonic time-delay reservoir computer dynamics |
| title_full_unstemmed | Hardware optimization for photonic time-delay reservoir computer dynamics |
| title_short | Hardware optimization for photonic time-delay reservoir computer dynamics |
| title_sort | hardware optimization for photonic time delay reservoir computer dynamics |
| topic | photonic time-delay reservoir computing bifurcation dynamics hyperparameter optimization |
| url | https://doi.org/10.1088/2634-4386/acb8d7 |
| work_keys_str_mv | AT mengzhang hardwareoptimizationforphotonictimedelayreservoircomputerdynamics AT zhizhuoliang hardwareoptimizationforphotonictimedelayreservoircomputerdynamics AT zrenahuang hardwareoptimizationforphotonictimedelayreservoircomputerdynamics |