<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[julyHawk的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/julyHawk</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; julyHawk]]></copyright><item><title><![CDATA[机器学习大作业：随机扩展shapelets变换代码调试记录]]></title><link>https://blog.youkuaiyun.com/julyHawk/article/details/135004815</link><guid>https://blog.youkuaiyun.com/julyHawk/article/details/135004815</guid><author>julyHawk</author><pubDate>Thu, 14 Dec 2023 21:27:59 +0800</pubDate><description><![CDATA[该研究介绍了一种随机扩张 Shapelet 变换算法 (RDST)。该方法可以在时间序列分类任务中发现重要的形状特征，以及提供对分类结果的可解释性。作者将 RDST 迁移到 aeon-toolkit 工具包中，通过该工具包可以使用最新版本的 RDST。]]></description><category></category></item><item><title><![CDATA[【论文笔记】基于半实例归一化和GMD损失函数的ECG信号降噪]]></title><link>https://blog.youkuaiyun.com/julyHawk/article/details/134563786</link><guid>https://blog.youkuaiyun.com/julyHawk/article/details/134563786</guid><author>julyHawk</author><pubDate>Wed, 22 Nov 2023 21:51:49 +0800</pubDate><description><![CDATA[这是一篇论文笔记，本文提出了一种基于半实例归一化块和梯度差分最大损失函数的深度学习去噪方法，用于心电图信号的降噪。该方法通过D-Unet和R-Unet两个网络阶段来实现去噪，并引入了GDM损失函数考虑信号的梯度差异。实验结果表明，该方法在信噪比和均方根误差等评价指标上取得了优秀的性能。]]></description><category></category></item><item><title><![CDATA[Macbook M1芯片安装openEuler虚拟机+优麒麟界面教程]]></title><link>https://blog.youkuaiyun.com/julyHawk/article/details/134513613</link><guid>https://blog.youkuaiyun.com/julyHawk/article/details/134513613</guid><author>julyHawk</author><pubDate>Mon, 20 Nov 2023 17:01:30 +0800</pubDate><description><![CDATA[本教程介绍了在MacBook上安装openEuler虚拟机并配置deepinUI界面的步骤。首先通过PD虚拟机安装openEuler，然后安装桌面UI，最后安装anaconda。（由Siyuan笔记-GPT-API整理）]]></description><category></category></item></channel></rss>