Encoding Optimization for Low-Complexity Spiking Neural Network Equalizers in IM/DD Systems

TL;DR

This paper introduces a reinforcement learning approach to optimize neural encoding parameters for spiking neural network equalizers in IM/DD systems, enhancing performance and efficiency.

Contribution

It presents a novel reinforcement learning algorithm for neural encoding optimization in SNNs, reducing complexity and improving system performance.

Findings

Improved equalizer performance in IM/DD systems.

Reduced computational load and network size.

Effective neural encoding parameter optimization.

Abstract

Neural encoding parameters for spiking neural networks (SNNs) are typically set heuristically. We propose a reinforcement learning-based algorithm to optimize them. Applied to an SNN-based equalizer and demapper in an IM/DD system, the method improves performance while reducing computational load and network size.