- 博客(268)
- 收藏
- 关注
转载 CF(协同过滤算法)
1 集体智慧和协同过滤1.1 什么是集体智慧(社会计算)? 集体智慧 (Collective Intelligence) 并不是 Web2.0 时代特有的,只是在 Web2.0 时代,大家在 Web 应用中利用集体智慧构建更加有趣的应用或者得到更好的用户体验。集体智慧是指在大量的人群的行为和数据中收集答案,帮助你对整个人群得到统计意义上的结论,这些结论是我们在单个个体上无法得到...
2019-01-20 14:12:24 1229
转载 推荐系统介绍
转自:https://www.cnblogs.com/redbear/p/8594939.html 推荐系统介绍当下,个性化推荐成了互联网产品的标配。但是,人们对推荐该如何来做,也就是推荐技术本身,还不甚了解。为此,好学的你肯定在收藏着朋友圈里流传的相关文章,转发着微博上的相关讨论话题,甚至还会不断奔走在各种大小行业会议之间,听着大厂职工们讲那些干货。我知道,这样碎片化的吸收,增加了知识...
2019-01-20 13:52:52 440
转载 推荐决策 对比user-based 和item-based推荐算法
from: http://www.hxxiaopei.com/?p=138最近在看项亮同学的推荐系统实践,整理一下思路。推荐系统,整体上有三种方式:user->user->item, 推荐与其相同兴趣的用户喜欢的item,user-baseduser->item->item, 推荐与其喜欢的item相似的i...
2019-01-20 11:37:33 821
转载 一道有意思的Amazon的概率面试题
该问题包含两个子问题:子问题1:给你一个骰子,你扔到几,机器将会给你相应的金钱。比如,你扔到6,机器会返回你6块钱,你扔到1,机器会返回你1块钱。请问,你愿意最多花多少钱玩一次?子问题2:在子问题1里,你只能扔一次,现在呢,可以给你两次机会,但是你自己...
2018-08-24 16:00:16 1318 1
转载 详解sklearn中logloss的计算过程
转自:http://blog.csdn.net/ybdesire/article/details/73695163 问题的引入用sklearn,计算loglosss时,对多类别问题,在用这样的代码进行计算(如下),会报错。其中y_true是真实值,y_pred是预测值y_true = [0,1...
2018-03-07 11:51:11 2943 1
转载 Word2vec加TextRank算法生成文章摘要
转自:http://blog.csdn.net/qq_22636145/article/details/75099792大数据时代的到来在给人们带来海量数据的便利的同时,也带来了大量的数据冗余和垃圾信息。传统的人工书写文本摘要是文章发布和文章阅读极为重要的一环,读者可以快速阅览摘要判断文章的续读必要性。 然而,人工智能的出现以及现在...
2018-03-06 13:56:55 2003
转载 最大似然估计(MLE)最大后验概率估计(MAP)以及贝叶斯公式的理解
转自: http://blog.csdn.net/u011508640/article/details/72815981最大似然估计(Maximum likelihood estimation, 简称MLE)和最大后验概率估计(Maximum a posteriori estimation, 简称MAP)是很常用的两种参数估计方法,如果不理解这两种方法的思路,很容易弄混...
2018-03-05 16:50:11 444
转载 极大似然估计
转自:http://blog.csdn.net/zengxiantao1994/article/details/72787849极大似然估计 以前多次接触过极大似然估计,但一直都不太明白到底什么原理,最近在看贝叶斯分类,对极大似然估计有了新的认识,总结如下:贝叶斯决策 首...
2018-03-05 16:31:09 295
转载 RF、GBDT、XGBoost整理
转自:http://blog.csdn.net/qq_28031525/article/details/70207918 由于本文是基于面试整理,因此不会过多的关注公式和推导,如果希望详细了解算法内容,敬请期待后文。 RF、GBDT和XGBoost都属于集成学习(Ense...
2018-03-04 10:39:18 323
转载 深度学习中常用的激励函数
转自:http://blog.csdn.net/rogerchen1983/article/details/79380567 我们知道深度学习的理论基础是神经网络,在单层神经网络中(感知机),输入和输出计算关系如下图所示: 可见,输入与输出是一个线性关系,对于增加了多...
2018-03-02 15:45:30 2070
转载 主成分分析(PCA)原理详解
转自:http://blog.csdn.net/zhongkelee/article/details/44064401一、PCA简介1. 相关背景 上完陈恩红老师的《机器学习与知识发现》和季海波老师的《矩阵代数》两门课之后,颇有体会。最近在做主成分分析和奇异值分解方面的项目,所以记录一下心得体会。&nbs...
2018-03-02 15:37:43 467
转载 Scikit-learn使用总结
转载自:https://www.jianshu.com/p/516f009c0875 在机器学习和数据挖掘的应用中,scikit-learn是一个功能强大的python包。在数据量不是过大的情况下,可以解决大部分问题。学习使用scikit-learn的过程中,我自己也在补充着机器学习和数据挖掘的知识。这里根据自己学习sklearn的经验,我做一个
2018-02-02 17:50:23 399
转载 python中常用的九种预处理方法
转自:http://www.jb51.net/article/92408.htm 本文总结的是我们大家在python中常见的数据预处理方法,以下通过sklearn的preprocessing模块来介绍;1. 标准化(Standardization or Mean Removal and Variance Scaling)变换后各维特征有0均值,单位方差。也叫z-sc
2018-02-02 17:40:19 934
转载 Scikit Learn CountVectorizer 入门实例
转自:http://blog.csdn.net/guotong1988/article/details/51567562from sklearn.feature_extraction.text import CountVectorizertexts=["dog cat fish","dog cat cat","fish bird", 'bird']cv = CountVectorizer
2018-02-02 16:46:47 537
转载 词性标注Pos Tagging
转自:http://blog.csdn.net/u014568921/article/details/51791495什么是词性标注,Part-of-speech tagging比如下面一段标注过词性的文字文字,用空格分开后,/前面的是英文单词,后面表示它的词性。[plain] view plain copy print?Confidence/NN in/IN the/DT p
2018-01-22 17:16:12 1012
转载 python中set和frozenset方法和区别
引自:https://www.cnblogs.com/panwenbin-logs/p/5519617.html set(可变集合)与frozenset(不可变集合)的区别:set无序排序且不重复,是可变的,有add(),remove()等方法。既然是可变的,所以它不存在哈希值。基本功能包括关系测试和消除重复元素. 集合对象还支持union(联合), intersection(交集)
2018-01-19 10:49:38 383
转载 LabelEncoder与OneHotEncoder
简单来说 LabelEncoder 是对不连续的数字或者文本进行编号from sklearn.preprocessing import LabelEncoderle = LabelEncoder()le.fit([1,5,67,100])le.transform([1,1,100,67,5])输出: array([0,0,3,2,1])OneHotEncoder 用于将表示
2018-01-18 16:09:58 617
转载 python中defaultdict方法的使用
转自:http://blog.csdn.net/real_ray/article/details/17919289 众所周知,在Python中如果访问字典中不存在的键,会引发KeyError异常(JavaScript中如果对象中不存在某个属性,则返回undefined)。但是有时候,字典中的每个键都存在默认值是非常方便的。例如下面
2018-01-18 14:27:18 359
原创 leetcode200. Number of Islands
200. Number of IslandsGiven a 2d grid map of ‘1’s (land) and ‘0’s (water), count the number of islands. An island is surrounded by water and is formed by connecting adjacent lands horizontally or verti
2017-09-29 21:25:41 324
原创 leetcode03. Find the Weak Connected Component in the Directed Graph
解法UnionFind/** * @Author RenXintao * @Date 9/20/17 * @method: UnionFind */class UnionFind { HashMap<Integer, Integer> father = new HashMap<>(); UnionFind(HashSet<Integer> hashSet) {
2017-09-20 22:01:09 436
原创 leetcode323. Number of Connected Components in an Undirected Graph
解法一bfs/** * @Author RenXintao * @Date 9/8/17 */class UndirectedGraphNode { int label; ArrayList<UndirectedGraphNode> neighbors; UndirectedGraphNode(int x) { label = x; ne
2017-09-08 20:15:22 467
原创 leetcode02 Triangle Count
triangle countGiven an array of integers, how many three numbers can be found in the array, so that we can build an triangle whose three edges length is the three numbers that we find?ExampleGiven arr
2017-09-06 22:00:18 417
原创 leetcode01. Two SumII
Given an array of integers, find how many pairs in the array such that their sum is bigger than a specific target number. Please return the number of pairs.解法排序+双指针/** * @Author RenXintao * @Date 9/6
2017-09-06 20:16:38 261
原创 leetcode1. Two Sum
1. Two SumGiven an array of integers, return indices of the two numbers such that they add up to a specific target.You may assume that each input would have exactly one solution, and you may not use th
2017-09-05 22:28:32 206
原创 Python Extended Slices eg[::-1]
Extended Slices>>> L = range(10)>>> L[::2][0, 2, 4, 6, 8]Negative values also work to make a copy of the same list in reverse order:>>> L[::-1][9, 8, 7, 6, 5, 4, 3, 2, 1, 0]This also works for tup
2017-08-03 15:40:11 521
转载 tensorflow报错:Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul')
tensorflow矩阵相乘,秩不同报错在tensorflow中写了这样一句:[python] view plain copy print?y_out = tf.matmul(outputs, W) y_out = tf.matmul(outputs, W)其中,outputs的shape为[16,336,400],W的shape为[400,1]出现以下报错:Shape must be r
2017-07-26 20:59:13 21946
原创 python [:-1]
w = [123, 234, 456] print 'w[-1]:', w[-1] ## 列表中的最后一个元素 print 'w[:-1]:', w[:-1] ## 除了列表中的最后一个元素w[-1]: 456w[:-1]: [123, 234]
2017-07-11 09:18:08 1451
原创 leetcode500. Keyboard Row
500. Keyboard RowGiven a List of words, return the words that can be typed using letters of alphabet on only one row’s of American keyboard like the image below.American keyboard Example 1: Input: [“
2017-06-28 23:34:28 317
原创 leetcode598. Range Addition II
598. Range Addition IIGiven an m * n matrix M initialized with all 0’s and several update operations.Operations are represented by a 2D array, and each operation is represented by an array with two pos
2017-06-28 22:53:47 245
原创 leetcode593. Valid Square
593. Valid SquareGiven the coordinates of four points in 2D space, return whether the four points could construct a square.The coordinate (x,y) of a point is represented by an integer array with two in
2017-06-28 22:42:53 451
原创 leetcode537. Complex Number Multiplication
537. Complex Number MultiplicationGiven two strings representing two complex numbers.You need to return a string representing their multiplication. Note i2 = -1 according to the definition.Example 1:I
2017-06-28 22:26:04 273
原创 论文《NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE》总结
NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE论文来源:Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv prepri
2017-06-28 20:53:48 2796
原创 论文《Aspect Level Sentiment Classification with Deep Memory Network》总结
Aspect Level Sentiment Classification with Deep Memory Network论文来源:Tang, D., Qin, B., & Liu, T. (2016). Aspect level sentiment classification with deep memory network. arXiv preprint arXiv:1605.08900.原
2017-06-27 09:26:32 1056
原创 论文《Recurrent Convolutional Neural Networks for Text Classification》总结
《Recurrent Convolutional Neural Networks for Text Classification》论文来源:Lai, S., Xu, L., Liu, K., & Zhao, J. (2015, January). Recurrent Convolutional Neural Networks for Text Classification. In AAAI (Vol
2017-06-26 22:05:13 13465 8
原创 论文《Convolutional Neural Networks for Sentence Classification》总结
《Convolutional Neural Networks for Sentence Classification》论文来源: Kim Y. Convolutional neural networks for sentence classification[J]. arXiv preprint arXiv:1408.5882, 2014.1.Introduction在Introduction部分
2017-06-26 15:20:59 12476
原创 leetcode617. Merge Two Binary Trees
617. Merge Two Binary TreesGiven two binary trees and imagine that when you put one of them to cover the other, some nodes of the two trees are overlapped while the others are not.You need to merge the
2017-06-25 21:32:44 270
原创 leetcode187. Repeated DNA Sequences
187. Repeated DNA SequencesAll DNA is composed of a series of nucleotides abbreviated as A, C, G, and T, for example: “ACGAATTCCG”. When studying DNA, it is sometimes useful to identify repeated sequen
2017-06-25 20:57:55 319
原创 leetcode77. Combinations
77. CombinationsGiven two integers n and k, return all possible combinations of k numbers out of 1 … n.For example, If n = 4 and k = 2, a solution is:[ [2,4], [3,4], [2,3], [1,2], [1,3]
2017-06-25 20:40:16 256
原创 leetcode47. Permutations II
47. Permutations IIGiven a collection of numbers that might contain duplicates, return all possible unique permutations.For example,[1,1,2] have the following unique permutations:[ [1,1,2], [1,2,
2017-06-25 20:20:18 195
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人