Multi-Task Learning to Enhance Generalizability of Neural Network Equalizers in Coherent Optical Systems

Antonio Napoli; Ashraful Alam; Bernhard Spinnler; Egor Sedov; Jaroslaw E. Prilepsky; Nelson Costa; Pedro J. Freire; Sasipim Srivallapanondh; Sergei K. Turitsyn

REVIEW

Multi-Task Learning to Enhance Generalizability of Neural Network Equalizers in Coherent Optical Systems

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.05374 v3 pith:5QJIHIPZ submitted 2023-07-04 eess.SP cs.LG

Sasipim Srivallapanondh , Pedro J. Freire , Ashraful Alam , Nelson Costa , Bernhard Spinnler , Antonio Napoli , Egor Sedov , Sergei K. Turitsyn

show 1 more author

Jaroslaw E. Prilepsky

This is my paper · ORCID

classification eess.SPcs.LG

keywords coherentequalizerslearningmulti-tasknn-basedsystemscompareddistance

verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments

read the original abstract

For the first time, multi-task learning is proposed to improve the flexibility of NN-based equalizers in coherent systems. A "single" NN-based equalizer improves Q-factor by up to 4 dB compared to CDC, without re-training, even with variations in launch power, symbol rate, or transmission distance.

Discussion (0). Continue with ORCID to comment.

Pith tools