VCSEL-based PAM-4 transmission system emulator: A data-driven deep learning perspective
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914579095748608 |
|---|---|
| author | Deligiannidis, Stavros Argyris, Nikos Dris, Stefanos Kalavrouziotis, Dimitris Bakopoulos, Paraskevas Mesaritakis, Charis Bogris, Adonis |
| author_facet | Deligiannidis, Stavros Argyris, Nikos Dris, Stefanos Kalavrouziotis, Dimitris Bakopoulos, Paraskevas Mesaritakis, Charis Bogris, Adonis |
| contents | We demonstrate a data-driven framework for emulating high-speed VCSEL-based 4-level Pulse Amplitude Modulation (PAM-4) optical interconnects using bidirectional Long Short-Term Memory (Bi-LSTM) networks. Unlike conventional rate-equation models, which are computationally intensive and often require difficult parameter tuning, our approach utilizes experimental waveforms to learn the end-to-end system dynamics. By employing transfer learning and weight interpolation, we extend the model to new operating regimes with a 20-fold reduction in computation time compared to independent training, while maintaining normalized mean squared error below 0.04. This emulator provides a rapid, accurate tool for the design and optimization of short-reach optical links. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18917 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VCSEL-based PAM-4 transmission system emulator: A data-driven deep learning perspective Deligiannidis, Stavros Argyris, Nikos Dris, Stefanos Kalavrouziotis, Dimitris Bakopoulos, Paraskevas Mesaritakis, Charis Bogris, Adonis Signal Processing Optics We demonstrate a data-driven framework for emulating high-speed VCSEL-based 4-level Pulse Amplitude Modulation (PAM-4) optical interconnects using bidirectional Long Short-Term Memory (Bi-LSTM) networks. Unlike conventional rate-equation models, which are computationally intensive and often require difficult parameter tuning, our approach utilizes experimental waveforms to learn the end-to-end system dynamics. By employing transfer learning and weight interpolation, we extend the model to new operating regimes with a 20-fold reduction in computation time compared to independent training, while maintaining normalized mean squared error below 0.04. This emulator provides a rapid, accurate tool for the design and optimization of short-reach optical links. |
| title | VCSEL-based PAM-4 transmission system emulator: A data-driven deep learning perspective |
| topic | Signal Processing Optics |
| url | https://arxiv.org/abs/2605.18917 |