基于深度学习的时间序列预测模型论文综述An Experimental Review on Deep Learning Architectures for Time Series Forecasting

论文题目:An Experimental Review on Deep Learning Architectures for Time Series Forecasting

介绍:这是一篇基于深度学习的用于时间序列预测模型综述型论文

论文:https://arxiv.org/pdf/2103.12057v2.pdf

说明:本文只是记录论文阅读中的学习笔记,整理一下,这篇综述所涉及的预测模型有七种:MLP、ERNN、LSTM、GRU、ESN、CNN、TCN,论文作者从预测精度和预测速度等方面对这其中模型进行了比较说明最后得出结论。

下面是本人在阅读论文中所做的一些总结,整理了一个思维导图

  • 0
    点赞
  • 15
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
摘要: 网络应用加密流量识别一直是网络安全领域中的重要问题之一。传统的加密流量识别方法主要基于特征提取和机器学习算法,但是这些方法存在着高维特征提取困难、易受攻击等问题。本文提出了一种基于深度学习的网络应用加密流量识别方法。该方法通过卷积神经网络对加密流量进行特征提取,结合全连接神经网络进行分类。实验结果表明,本方法能够有效地识别不同的网络应用加密流量,具有较高的准确率和鲁棒性。 关键词:深度学习;加密流量识别;卷积神经网络;全连接神经网络 Abstract: Network application encrypted traffic identification has always been one of the important problems in the field of network security. Traditional encrypted traffic identification methods are mainly based on feature extraction and machine learning algorithms, but these methods have problems such as difficult high-dimensional feature extraction and vulnerability to attacks. This paper proposes a network application encrypted traffic identification method based on deep learning. This method uses convolutional neural networks to extract features from encrypted traffic and combines them with fully connected neural networks for classification. Experimental results show that this method can effectively identify different network application encrypted traffic, with high accuracy and robustness. Keywords: deep learning; encrypted traffic identification; convolutional neural network; fully connected neural network

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值