An Improved Neural Network Pruning Technology for Automatic Modulation Classification in Edge Devices
Yun Lin, Ya Tu, Zheng Dou
Abstract
Automatic modulation classification (AMC) plays an important role in both civilian and military applications. Today, increasingly more researchers apply a deep learning framework in AMC. However, few papers take into account that a typical deep model is difficult to deploy on resource constrained devices. In this paper, we propose a new filter-level pruning technique based on activation maximization (AM) that omits the less important convolutional filter. Compared to other network pruning techniques, the convolutional neural network pruned via the AM method achieves equal or higher classification accuracy in the RadioML2016.10a dataset.
Topics & Concepts
Convolutional neural networkPruningComputer scienceArtificial intelligenceDeep learningMachine learningEdge deviceFilter (signal processing)Enhanced Data Rates for GSM EvolutionArtificial neural networkMaximizationPattern recognition (psychology)MathematicsComputer visionCloud computingAgronomyOperating systemMathematical optimizationBiologyWireless Signal Modulation Classification