Optics Letters · 2024 · 15 citations · 12 references
EngineeringComputer ScienceElectrical EngineeringAnalog ElectronicsLow-power DesignPhotonicsData CompressionDigital Signal ProcessingAdaptive QuantizationDirect DetectionEqualizationFloating-point ArithmeticHardware ResourcesNeural Network QuantizationPartitioningQuantization
Neural network (NN)-based equalizers have been widely applied for dealing with nonlinear impairments in intensity-modulated direct detection (IM/DD) systems due to their excellent performance. However, the computational complexity (CC) is a major concern that limits the real-time application of NN-based receivers. In this Letter, we propose, to our knowledge, a novel weight-adaptive joint mixed-precision quantization and pruning approach to reduce the CC of NN-based equalizers, where only integer arithmetic is taken into account instead of floating-point operations. The NN connections are either directly cutoff or represented by a proper number of quantization bits by weight partitioning, leading to a hybrid compressed sparse network that computes much faster and consumes less hardware resources. The proposed approach is verified in a 50-Gb/s 25-km pulse amplitude modulation (PAM)-4 IM/DD link using a directly modulated laser (DML) in the C-band. Compared with the traditional fully connected NN-based equalizer operated with standard floating-point arithmetic, about 80% memory can be saved at a minimum network size without degrading the system performance. Quantization is also shown to be more suitable to over-parameterized NN-based equalizers compared with NNs selected at a minimum size.
12
200 Gbps/Lane IM/DD Technologies for Short Reach Optical Interconnects
Xiaodan Pang, Oskars Ozoliņš, Rui Lin et al. · Journal of Lightwave Technology · 2019 · 203 citations · Full text
Boris Karanov, Domaniç Lavery, Polina Bayvel et al. · Repository KITopen (Karlsruhe Institute of Technology) · 2019 · 88 citations · Full text