Principles and Metrics of Extreme Learning Machines Using a Highly Nonlinear Fiber
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915529479946240 |
|---|---|
| author | Hary, Mathilde Brunner, Daniel Leybov, Lev Ryczkowski, Piotr Dudley, John M. Genty, Goëry |
| author_facet | Hary, Mathilde Brunner, Daniel Leybov, Lev Ryczkowski, Piotr Dudley, John M. Genty, Goëry |
| contents | Optical computing offers potential for ultra high-speed and low latency computation by leveraging the intrinsic properties of light. Here, we explore the use of highly nonlinear optical fibers (HNLFs) as platforms for optical computing based on the concept of Extreme Learning Machines. Task-independent evaluations are introduced to the field for the first time and focus on the fundamental metrics of effective dimensionality and consistency, which we experimentally characterize for different nonlinear and dispersive conditions. We show that input power and fiber characteristics significantly influence the dimensionality of the computational system, with longer fibers and higher dispersion producing up to 100 principal components (PCs) at input power levels of 30 mW, where the PC correspond to the linearly independent dimensions of the system. The spectral distribution of the PC's eigenvectors reveals that the high-dimensional dynamics facilitating computing through dimensionality expansion are located within 40~nm of the pump wavelength at 1560~nm, providing general insight for computing with nonlinear Schrödinger equation systems. Task-dependent results demonstrate the effectiveness of HNLFs in classifying MNIST dataset images. Using input data compression through PC analysis, we inject MNIST images of various input dimensionality into the system and study the impact of input power upon classification accuracy. At optimized power levels we achieve a classification test accuracy of 88\%, significantly surpassing the baseline of 83.7\% from linear systems. Noteworthy, we find that best performance is not obtained at maximal input power, i.e. maximal system dimensionality, but at more than one order of magnitude lower. The same is confirmed regarding the MNIST image's compression, where accuracy is substantially improved when strongly compressing the image to less than 50 PCs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05233 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Principles and Metrics of Extreme Learning Machines Using a Highly Nonlinear Fiber Hary, Mathilde Brunner, Daniel Leybov, Lev Ryczkowski, Piotr Dudley, John M. Genty, Goëry Optics Emerging Technologies Optical computing offers potential for ultra high-speed and low latency computation by leveraging the intrinsic properties of light. Here, we explore the use of highly nonlinear optical fibers (HNLFs) as platforms for optical computing based on the concept of Extreme Learning Machines. Task-independent evaluations are introduced to the field for the first time and focus on the fundamental metrics of effective dimensionality and consistency, which we experimentally characterize for different nonlinear and dispersive conditions. We show that input power and fiber characteristics significantly influence the dimensionality of the computational system, with longer fibers and higher dispersion producing up to 100 principal components (PCs) at input power levels of 30 mW, where the PC correspond to the linearly independent dimensions of the system. The spectral distribution of the PC's eigenvectors reveals that the high-dimensional dynamics facilitating computing through dimensionality expansion are located within 40~nm of the pump wavelength at 1560~nm, providing general insight for computing with nonlinear Schrödinger equation systems. Task-dependent results demonstrate the effectiveness of HNLFs in classifying MNIST dataset images. Using input data compression through PC analysis, we inject MNIST images of various input dimensionality into the system and study the impact of input power upon classification accuracy. At optimized power levels we achieve a classification test accuracy of 88\%, significantly surpassing the baseline of 83.7\% from linear systems. Noteworthy, we find that best performance is not obtained at maximal input power, i.e. maximal system dimensionality, but at more than one order of magnitude lower. The same is confirmed regarding the MNIST image's compression, where accuracy is substantially improved when strongly compressing the image to less than 50 PCs. |
| title | Principles and Metrics of Extreme Learning Machines Using a Highly Nonlinear Fiber |
| topic | Optics Emerging Technologies |
| url | https://arxiv.org/abs/2501.05233 |