首页> 外文会议>International Conference on Artificial Neural Networks >Multi-objective Pruning for CNNs Using Genetic Algorithm
【24h】

Multi-objective Pruning for CNNs Using Genetic Algorithm

机译:基于遗传算法的CNN多目标修剪

获取原文

摘要

In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity. In our experiments, we apply our approach to prune pre-trained LeNet across the MNIST dataset, which reduces 95.42% parameter size and achieves 16 times speedups of convolutional layer computation with tiny accuracy loss by laying emphasis on sparsity and computation, respectively. Our empirical study suggests that GA is an alternative pruning approach for obtaining a competitive compression performance. Additionally, compared with state-of-the-art approaches, GA can automatically pruning CNNs based on the multi-objective importance by a pre-defined fitness function.
机译:在这项工作中,我们根据错误,计算和稀疏性之间的多目标权衡,提出了一种用于修剪卷积神经网络(CNN)的启发式遗传算法(GA)。在我们的实验中,我们将方法应用于在MNIST数据集上修剪经过预训练的LeNet,通过分别强调稀疏性和计算,减少了95.42%的参数大小并实现了16倍的卷积层计算加速,而精度损失却很小。我们的经验研究表明,GA是获得竞争性压缩性能的另一种修剪方法。此外,与最新技术相比,GA可以通过预定义的适应度函数基于多目标重要性自动修剪CNN。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号