<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[不行不至]]></title><description><![CDATA[Life is hard no matter where we live.]]></description><link>https://blog.youkuaiyun.com/Void_worker</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; Void_worker]]></copyright><item><title><![CDATA[扩展归并排序--小和问题/逆序对问题]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/104932199</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/104932199</guid><author>Void_worker</author><pubDate>Tue, 17 Mar 2020 22:07:59 +0800</pubDate><description><![CDATA[问题描述
一个数列，其中一个数p，其左边所有比p小的数的和，是数p的小和。
求这个数列所有数的小和之和。
例子：
[3, 1, 4, 5, 2]
3左边比3小的数：
1左边比1小的数：
4左边比4小的数：3, 1
5左边比5小的数：3, 1, 4
2左边比2小的数：1
把这些数求和得到的就是小和： 13
解法
(1)暴力解法，遍历。T=O(n^2)
(2)归并排序
复习归并排序：
a.首先划分，一...]]></description><category></category></item><item><title><![CDATA[pycharm下远程连接服务器jupyter notebook]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/101199850</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/101199850</guid><author>Void_worker</author><pubDate>Mon, 23 Sep 2019 12:29:43 +0800</pubDate><description><![CDATA[0.准备环境
本地pycharm professional版本
服务器: 安装jupyter notebook(conda命令,pip命令)
pycharm 已经远程连接服务器
1.服务器端jupyter设置
生成配置文件
jupyter notebook --generate-config

设置密码
jupyter notebook password

打开配置文件
vi ~/.jupyter...]]></description><category></category></item><item><title><![CDATA[世界人工智能大会-杨强演讲内容ppt]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/100166218</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/100166218</guid><author>Void_worker</author><pubDate>Fri, 30 Aug 2019 21:18:20 +0800</pubDate><description><![CDATA[世界人工智能大会-杨强演讲内容ppt



]]></description><category></category></item><item><title><![CDATA[吐血整理-周志华演讲合集]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/100165433</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/100165433</guid><author>Void_worker</author><pubDate>Fri, 30 Aug 2019 20:38:32 +0800</pubDate><description><![CDATA[前言:
这是整理了周志华老师几个演讲笔记的合集，很齐全啊哈哈哈哈，欢迎大家留言补充]]></description><category></category></item><item><title><![CDATA[使用anaconda安装python3版本的PIL]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/99627783</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/99627783</guid><author>Void_worker</author><pubDate>Thu, 15 Aug 2019 12:03:11 +0800</pubDate><description><![CDATA[最近在做图像分割，在服务器上打算装个基于python3的环境。
conda create -n env_m python=3.5以后，
一直在用conda install 各种库，所有的库都装完以后发现，所有的东西都变成了python2…
一步步重新试了下，发现是在安装PIL的过程中，PIL把我的py3都变成了py2，坑啊，如下图

网上搜了一下，才发现PIL仅支持到python2.7，所以我安装...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(10)--Blending and Bagging（台大林轩田视频）]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/99441610</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/99441610</guid><author>Void_worker</author><pubDate>Tue, 13 Aug 2019 15:49:14 +0800</pubDate><description><![CDATA[文章目录1.Aggregation model2.Blending(混合)2.1 Uniform blending(voting)2.2 Linear and any blending3.Bagging(bootstrap aggregation BAGging)
本节课主要介绍Aggregation Models，目的是将不同的hypothesis得到的g集合起来，利用集体智慧得到更好的预测模型...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(9)--support vector machine(SVM)（台大林轩田SVM）]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/98470389</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/98470389</guid><author>Void_worker</author><pubDate>Sun, 04 Aug 2019 17:18:53 +0800</pubDate><description><![CDATA[文章目录1. Liner Support Vector Machine1.1 SVM引出1.2 SVM中的margin计算1.3 margin计算公式的简化1.4 SVM一般求解方法1.5 非线性SVM2.Dual Support Vector Machine2.1 Dual SVM引出2.2 Lagrange Function 拉格朗日函数2.3 把SVM构造成非条件问题2.4 Lagrange...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(9)--support vector machine(SVM)]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/97290146</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/97290146</guid><author>Void_worker</author><pubDate>Thu, 25 Jul 2019 20:15:41 +0800</pubDate><description><![CDATA[文章目录1.SVM cost function 代价函数2.Hypothesis function 假设函数3.large margin intuition 大间距分类器4.Kernels 核函数4.1相似度函数similarity function 核函数kernels4.2 核函数标记点landmark4.3 SVM参数选择5.其他
1.SVM cost function 代价函数
SVM c...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(8)--logistic regression]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/96384386</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/96384386</guid><author>Void_worker</author><pubDate>Wed, 17 Jul 2019 23:42:49 +0800</pubDate><description><![CDATA[文章目录0.逻辑回归的引出1.假设函数hypothesis function2.代价函数cost function
0.逻辑回归的引出
对分类问题应用线性回归不是一个好主意
二分类问题：
0：negative class
1：positive class
If h(x)&gt;0.5, predict y=1
If h(x)&lt;0.5, predict y=0
Logistic regress...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(7)--牛顿法]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/95989945</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/95989945</guid><author>Void_worker</author><pubDate>Mon, 15 Jul 2019 17:33:46 +0800</pubDate><description><![CDATA[本文来自：https://blog.youkuaiyun.com/qq_36330643/article/details/78003952
在第2部分求最优化的地方做了更改。
牛顿法有两个应用方向：
1.求方程的根
2.最优化
1.求方程的根
并不是所有的方程都有求根公式，或者求根公式很复杂，导致求解困难。利用牛顿法，可以迭代求解。
原理是利用泰勒公式，在x0处展开，且展开到一阶，即f(x) = f(x0)+...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(6)--EM算法详细讲解]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/94859381</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/94859381</guid><author>Void_worker</author><pubDate>Sat, 06 Jul 2019 15:13:16 +0800</pubDate><description><![CDATA[以下是我看了两个b站视频的学习笔记，视频讲的很详细，我整理的也就比较详细，非常容易理解。
视频连接：
https://www.bilibili.com/video/av24989947
https://www.bilibili.com/video/av25304979
文章目录EM算法举例：从投币试验看EM算法补充
首先了解下什么是混合模型：
Hard clustering:硬性聚类:数据点要么属...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(5)--朴素贝叶斯分类器]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/94859241</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/94859241</guid><author>Void_worker</author><pubDate>Sat, 06 Jul 2019 15:04:01 +0800</pubDate><description><![CDATA[朴素贝叶斯分类器
模型评价：
优点：在数据较少的情况下仍然有效，可以处理多类别问题
缺点：对于输入数据的准备方式较为敏感
适用数据类型：标称型数据
贝叶斯决策理论的核心思想：选择具有最高概率的决策
条件概率
计算条件概率的方法
①条件概率计算公式： p(B∣A)=P(AB)P(A)p(B|A) = \frac{P(AB)}{P(A)}p(B∣A)=P(A)P(AB)​
②贝叶斯准则：贝叶斯准则告诉...]]></description><category></category></item><item><title><![CDATA[光声成像]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/94479854</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/94479854</guid><author>Void_worker</author><pubDate>Tue, 02 Jul 2019 20:51:30 +0800</pubDate><description><![CDATA[文章目录1.光声成像简介2.光声成像分类3.图像重建算法4.光声成像系统三个典型问题5.挑战
光声成像之前的成像方式对比
X射线成像：
优点：能对骨头和硬组织进行深度成像，有着很强的对比度和极高的分辨率
缺点：对软组织成像很差，能反映的功能信息少，对人体有伤害
超声成像（USI）
优点：安全、费用低、易于携带、分辨率高。陈横向深度深、对声阻抗匹配好的组织灵敏度高，对软组织成像对比度高
缺点：骨头和...]]></description><category></category></item><item><title><![CDATA[机器学习笔记--常见算法(2)--决策树算法介绍]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/93486923</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/93486923</guid><author>Void_worker</author><pubDate>Mon, 24 Jun 2019 15:25:00 +0800</pubDate><description><![CDATA[文章目录1.决策树简介2.决策树Decision Tree3.特征选择3.1 信息增益3.2 信息增益比3.3 Gini系数4.决策树的生成5.决策树的剪枝6.连续与缺失值6.1 连续值处理6.2 缺失值处理
1.决策树简介
决策树：既能做分类，又能做回归
决策树模型是一种传统的算法，决策树实际上就是在模仿人类做决策的过程。
可以从两个方面来理解决策树:
（1）Aggregation model
...]]></description><category></category></item><item><title><![CDATA[机器学习简史]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/90734369</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/90734369</guid><author>Void_worker</author><pubDate>Sat, 01 Jun 2019 22:37:14 +0800</pubDate><description><![CDATA[本文是Brief History of Machine Learning 的译文，原文链接：http://www.erogol.com/brief-history-machine-learning/

文章目录1949年 Donald Hebb(赫步)：赫布理论1952年 Arthur Samuel(亚瑟·塞缪尔)：西洋跳棋程序1957年 Rosenblatt(罗森布拉特)：感知机1960年 W...]]></description><category></category></item><item><title><![CDATA[人工智能发展史（读书笔记）]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/90669308</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/90669308</guid><author>Void_worker</author><pubDate>Wed, 29 May 2019 13:29:37 +0800</pubDate><description><![CDATA[有关人工智能历史的书籍我看了尼克的《人工智能简史》和集智俱乐部的《科学的极致：漫谈人工智能》部分章节。阅读体验是《科学的极致》一书更系统和条理，《人工智能简史》更偏细节，有点琐碎。可以先看《科学的极致》搭起整个发展历史框架，再看《人工智能简史》了解更多细节问题。下面是我看了《科学的极致》中人工智能发展历史一章的读书笔记。基本就是一个简略的历史发展框架~
有不对的地方还请大家多多指正~ 谢谢大嘎 ~...]]></description><category></category></item><item><title><![CDATA[周读论文系列笔记(4)-reivew-Image registration methods: a survey]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/86149412</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/86149412</guid><author>Void_worker</author><pubDate>Wed, 09 Jan 2019 14:04:49 +0800</pubDate><description><![CDATA[文章目录1. Introduction2. Image registration methodology3. Step1: Feature detection3.1 Area-based methods3.2 Feature-based methods4. Step2: Feature matching4.1 Area-based methods4.2 Feature-based methods5...]]></description><category></category></item><item><title><![CDATA[周读论文系列笔记(3)-reivew-A survey of medical image regstration - under revew]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/85387462</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/85387462</guid><author>Void_worker</author><pubDate>Sun, 30 Dec 2018 14:43:24 +0800</pubDate><description><![CDATA[原文链接;https://www.sciencedirect.com/science/article/pii/S1361841516301074
1. A scheme to classify image registration methods
(i) dimensionality (spatial or spatiotemporal 2D/2D, 2D/3D, 3D/3D),
(ii) nat...]]></description><category></category></item><item><title><![CDATA[周读论文系列笔记(2)-reivew-A survey on Deep Learning in Medical Image Analysis]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/85317382</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/85317382</guid><author>Void_worker</author><pubDate>Sat, 29 Dec 2018 13:52:21 +0800</pubDate><description><![CDATA[
刚接触这个领域…不怎么会写…有些翻译错和理解错的地方请大佬们多多指教~

原文链接：
文章目录1.Deep learning methods2.Deep learning uses in medical imaging2.1 Classification 分类2.1.1 Image/exam classification （图像/exam 分类）2.1.2 Object or lesion cl...]]></description><category></category></item><item><title><![CDATA[周读论文系列笔记(1)-review-Artificial intelligence in healthcare]]></title><link>https://blog.youkuaiyun.com/Void_worker/article/details/85290027</link><guid>https://blog.youkuaiyun.com/Void_worker/article/details/85290027</guid><author>Void_worker</author><pubDate>Thu, 27 Dec 2018 17:01:06 +0800</pubDate><description><![CDATA[
第一次…不知道怎么写，好纠结(꒦_꒦)

原文链接：
论文分为3个部分，也就是本文的目录
文章目录1.A historical overview of AI in medicine2.Recent breakthroughs in AI technologies and their biomedical applications2.1 Image-based diagnosis 基于图像的诊断2...]]></description><category></category></item></channel></rss>