Spiking Neural Network Decision Feedback Equalization for IM/DD Systems

However, the performance of most equalizers depends on their complexity, leading to power-hungry receivers when implemented on digital hardware. Compared to conventional digital hardware, neuromorphic hardware can massively reduce energy consumption when solving the same tasks [1]. Spiking neural networks (SNNs) implemented on neuromorphic hardware mimic the human brain's behavior and promise energy-efficient, low-latency processing [2]. In [3], an SNN-based equalizer with a decision feedback structure (SNN-DFE) has been proposed for equalization and demapping based on future and currently received, and already decided symbols. For different multipath scenarios, i.e., linear channels, the SNN-DFE performs similarly to the classical decision feedback equalizer (CDFE) and artificial neural network (ANN) based equalizers. For a 4-fold pulse amplitude modulation (PAM4) transmitted over an intensity modulation / direct detection (IM/DD) link suffering from chromatic dispersion (CD) and non-linear impairments, [4] proposes an SNN that estimates the transmit symbols based on received symbols without feedback, no-feedback-SNN (NF-SNN).