AI Article Synopsis
- A new type of neural network called VINN is introduced to address the complexity issues found in traditional Volterra nonlinear equalizers.
- By fine-tuning how solutions are calculated, VINN uses fewer computational resources while still effectively handling nonlinear signals.
- Testing on an FPGA system shows VINN can process signals at 240 Gb/s, achieving a high net rate of 180 Gb/s while meeting error correction standards.
Article Abstract
A white-box power-lite Volterra-inspired neural network (VINN) equalizer is proposed to solve the problem of complexity discontinuity in a Volterra nonlinear equalizer (VNLE). By adjusting the granularity of the solution space, it conserves computational resources while maintaining nonlinear compensation capability. The performance of VINN is verified on a field-programmable gate array (FPGA) in a short-reach intensity modulation and direct detection (IMDD) system, and a 240-Gb/s real-time signal processing rate is achieved. Under the 25% overhead soft-decision forward error correction (SD-FEC) bit error rate (BER) threshold, we realize a record net rate of up to 180 Gb/s based on the FPGA.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OL.533564 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Article Synopsis
- A new type of neural network called VINN is introduced to address the complexity issues found in traditional Volterra nonlinear equalizers.
- By fine-tuning how solutions are calculated, VINN uses fewer computational resources while still effectively handling nonlinear signals.
- Testing on an FPGA system shows VINN can process signals at 240 Gb/s, achieving a high net rate of 180 Gb/s while meeting error correction standards.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!