Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection

12/08/2022

∙

To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38% latency decrease, while impacting the Q-factor by only 0.5dB.

READ FULL TEXT

Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection

On Compressing U-net Using Knowledge Distillation

Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization

Fast Video Salient Object Detection via Spatiotemporal Knowledge Distillation

Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss

Exploring the Connection between Knowledge Distillation and Logits Matching

Low-resource Low-footprint Wake-word Detection using Knowledge Distillation

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection

Related Research

On Compressing U-net Using Knowledge Distillation

Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization

Fast Video Salient Object Detection via Spatiotemporal Knowledge Distillation

Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss

Exploring the Connection between Knowledge Distillation and Logits Matching

Low-resource Low-footprint Wake-word Detection using Knowledge Distillation

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems