【24h】

Design of Improved Deep Convolution Network Model

机译:改进深卷积网络模型的设计

获取原文

摘要

Convolution neural network is a feed-forward neural network which contains convolution calculation and has depth structure. In this paper, the basic structure and operation principle of convolution neural network are analyzed. CNN has the best effect in handwritten recognition, and the application of CNN in face-based gender recognition is also very good. In this paper, the factors that influence the convolution neural network model are analyzed. In this paper, the improved deep convolution network model is proposed, and the results show that the improved method can effectively improve the classification effect and classification accuracy of the convolution neural network.
机译:卷积神经网络是一种前馈神经网络,包含卷积计算并具有深度结构。本文分析了卷积神经网络的基本结构和操作原理。 CNN在手写识别方面具有最佳效果,CNN在基于面部性别识别中的应用也非常好。本文分析了影响卷积神经网络模型的因素。在本文中,提出了改进的深度卷积网络模型,结果表明,改进的方法可以有效地提高卷积神经网络的分类效果和分类准确性。

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