Saved in:
Bibliographic Details
Main Authors: Obeed, Mohanad, Jian, Ming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.20084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912813098729472
author Obeed, Mohanad
Jian, Ming
author_facet Obeed, Mohanad
Jian, Ming
contents Towards fast, hardware-efficient, and low-complexity receivers, we propose a compression-aware learning approach and examine it on free-space optical (FSO) receivers for turbulence mitigation. The learning approach jointly quantize, prune, and train a convolutional neural network (CNN). In addition, we propose to have the CNN weights of power of two values so we replace the multiplication operations bit-shifting operations in every layer that has significant lower computational cost. The compression idea in the proposed approach is that the loss function is updated and both the quantization levels and the pruning limits are optimized in every epoch of training. The compressed CNN is examined for two levels of compression (1-bit and 2-bits) over different FSO systems. The numerical results show that the compression approach provides negligible decrease in performance in case of 1-bit quantization and the same performance in case of 2-bits quantization, compared to the full-precision CNNs. In general, the proposed IM/DD FSO receivers show better bit-error rate (BER) performance (without the need for channel state information (CSI)) compared to the maximum likelihood (ML) receivers that utilize imperfect CSI when the DL model is compressed whether with 1-bit or 2-bit quantization.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20084
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint Quantization and Pruning Neural Networks Approach: A Case Study on FSO Receivers
Obeed, Mohanad
Jian, Ming
Signal Processing
Towards fast, hardware-efficient, and low-complexity receivers, we propose a compression-aware learning approach and examine it on free-space optical (FSO) receivers for turbulence mitigation. The learning approach jointly quantize, prune, and train a convolutional neural network (CNN). In addition, we propose to have the CNN weights of power of two values so we replace the multiplication operations bit-shifting operations in every layer that has significant lower computational cost. The compression idea in the proposed approach is that the loss function is updated and both the quantization levels and the pruning limits are optimized in every epoch of training. The compressed CNN is examined for two levels of compression (1-bit and 2-bits) over different FSO systems. The numerical results show that the compression approach provides negligible decrease in performance in case of 1-bit quantization and the same performance in case of 2-bits quantization, compared to the full-precision CNNs. In general, the proposed IM/DD FSO receivers show better bit-error rate (BER) performance (without the need for channel state information (CSI)) compared to the maximum likelihood (ML) receivers that utilize imperfect CSI when the DL model is compressed whether with 1-bit or 2-bit quantization.
title Joint Quantization and Pruning Neural Networks Approach: A Case Study on FSO Receivers
topic Signal Processing
url https://arxiv.org/abs/2506.20084