- 博客(30)
- 收藏
- 关注
转载 Tensorflow--Day 1
import tensorflow as tf# Model parametersW = tf.Variable([.3], dtype=tf.float32)b = tf.Variable([-.3], dtype=tf.float32)# Model input and outputx = tf.placeholder(tf.float32)linear_model = W * x +
2017-10-09 06:31:40
357
1
原创 Algorithms
Programming Thoughts:Reasoning thought; Recursive though; Greedy thought; Enumeration thought; Divid and Conquer; Backtracking; Dynamic Programming; Probability thoughtSorting:Internal sort:All data ha
2017-10-09 04:04:22
340
原创 文章标题
(笔记总结需要!目前粗糙潦草,后期会不断修改。若对您阅读造成不便,望请见谅!!)8. PCAA dimensionality reduction algorithm that can be able to significantly speed up unsupervised feature learning algorithm. More importantly, understanding PC
2017-10-09 03:54:24
158
原创 Autoencoders
(笔记总结需要!目前粗糙潦草,后期会不断修改。若对您阅读造成不便,望请见谅!!)7.Autoencoders:compress features, same function like PCAs.
2017-10-09 03:53:37
219
原创 CNN
(笔记总结需要!目前粗糙潦草,后期会不断修改。若对您阅读造成不便,望请见谅!!)6. CNN1.initialize paremeters and load data.–>2. Bulid model.–>3. compute loss.–>4. Backpropagation.–>5. adjust parametersFully conntected network: all inputs in
2017-10-09 03:52:46
229
原创 SVM
(笔记总结需要!目前粗糙潦草,后期会不断修改。若对您阅读造成不便,望请见谅!!)4. SVMSVM的学习策略是间隔最大化。SVM的学习算法是求解凸优化规划(convex quadratic programming)的最优化算法。三种由简至繁的模型:Linear SVM in linearly separable case, linear SVM 和Nonlinear SVM。
2017-10-09 03:50:43
176
原创 Boost
3. Boost AlgorithmsAdaBoost算法: 综合多个分类器,得到更精确结果。AdaBoost思想: 1、多轮训练,多个分类器 2、每轮训练增加错误样本的权值,降低正确分类样本权值。 3、降低错误率高的分类器权值,增加正确率高的分类器权值。
2017-10-09 03:49:30
165
原创 KNN
(笔记总结需要!目前粗糙潦草,后期会不断修改。若对您造成不便,望请见谅!!)2. KNN参考链接:http://www.hankcs.com/ml/k-nearest-neighbor-method.html2.1 KNN算法给定一个训练数据集,对新的输入实例,在训练数据集中找到跟它最近的k个实例,根据这k个实例的类判断它自己的类(一般采用多数表决的方法)。KNN模型: 三要素:距离度量方法、K值
2017-10-09 03:33:17
275
转载 Decision Tree
1. Decision TreeReference:http://www.hankcs.com/ml/decision-tree.html代码用ID3生成算法和C4.5生成算法实现,并用matplotlib可视化出来。分类决策树是对实例进行分类的树形结构。由结点和有向边组成。结点分为内部结点和叶节点。内部结点表示一个特征或属性,叶节点表示一个类。分类时,从根节点出发,当前结点设为根节点,且当前结点必
2017-10-09 03:30:11
252
原创 Dynamic Programming--Algorithms
EditDistance(A[1. . . n],B [1. . . m])D(i,0)← iand D(0,j)← jfor all i,jfor jfrom 1to m: for ifrom 1to n: insertion← D(i, j− 1) +1 delet
2017-09-30 22:10:19
358
原创 Greatest common divisors & Fibonacci Numbers--Algorithms
Greatest Common Divisors:Naive Algorithm: Function NaiveGCD(a,b)best ←0for dfrom 1to a+b: if d|aand d|b: best← dreturn best
2017-09-30 15:30:35
149
原创 Graphs--Data Structure
DefinitionAn (undirected) Graph is a collection V of vertices, and a collection E ofedges each of which connects a pair of vertices.Vertices: A,B,C,D
2017-09-30 14:36:34
292
原创 Greedy Algorithm--Algorithms
Largest Number: Find max digit Append it to the number Remove it from the list of digits Repeat while there are digits in the list car fueling: Refill at the
2017-09-30 14:23:24
550
原创 AVL tree--Data Structure
HeightDefinitionThe heightof a node is the maximum depth of its subtree.AVL PropertyAVL trees maintain the following propert
2017-09-30 13:47:38
195
原创 Binary Search Tree--Data Structure
Hash tableRangeSearch: impossibleNearestNeighbors: impossibleInsert: O(1)Delete: O(1)Array:RangeSearch: O(n)NearestNeighbors: O(n)Insert: O(1)Delete
2017-09-30 12:27:16
176
原创 Hash Tables: String Search--Data Structure
Naive AlgorithmFor each position i from 0 to |T| − |P|,check character-by-character whetherT[i..i+ |P| −1] = Por not. If yes, append i to the result.
2017-09-30 12:12:16
146
原创 Hash Tables: Distributed Hash Tables--Data Structure
upload file instantly.Naive Comparison Upload new file Go through all stored files Compare each stored file with new file byte-by-byte If there's the same file, sto
2017-09-30 11:46:38
220
原创 Hash Table: Hash Functions--Data Structure
Phone BookDesign a data structure to store your contacts: names of people along with their phone numbers. The data structure should be able to do the following quickly: Add and
2017-09-30 11:04:00
191
原创 Basics of Hash Table--Data Structure
Intro:API: Python: Dict; JAVA: HashMapApplications: File Systems; Password Verification; Store OptimizationIP Address: Main Looplog - array of log lines(tim
2017-09-30 09:16:42
222
原创 Disjoint Sets--Data Structure
Naive algorithm:A disjoint-set data structure supports the following operations: MakeSet(x) creates a singleton set {x} Find(x) returns ID of the set containing x: if x and y lie in the
2017-09-30 08:37:08
313
原创 Priority Queue--Data Structure
(一)Main operations of a queue: PushBack(e); PopFront().Priority queue is a generalization of a queue where each element is assigned a priority and elements come out in order by priority.
2017-09-30 07:30:22
288
原创 Dynamic Array--Data Structure
Time complexity of Runtime:Get(i) O(1)Set(i, val) O(1)PushBack(val) O(n)Remove(i) O(n)Size() O(1)Common Implementations:C++ : Vector
2017-09-29 10:01:08
402
原创 DFS & BFS--Data Structure
Two ways of traversal : DFS, BFSThree methods to implement DFS:InOrderTraversal (tree) if (tree == null) return; InOrderTraversal (tree.left); Print (tree.key); InOrderTraversal (t
2017-09-29 09:23:31
159
原创 Basic Tree--Data Structure
Pseudocode:Height (tree)if (tree == null) return 0;return 1 + Max ( Height ( tree.left ), Height ( tree.right ));Size (tree)if (tree == null) return 0;return 1 + Size ( tree.left) +Siz
2017-09-29 09:01:32
267
原创 Stack & Queue--Data Structure
Stack:Queue:在队列中,如果enqueue操作因为长度限制而从左向右压入数据,保留一个空间作为首尾的区分。
2017-09-29 08:10:45
674
原创 Single Linked List--Data Structure
单链表形式如上图所示,内部包含“key”和“next pointer”指针,且指向一个方向。API操作的时间复杂度:
2017-09-29 07:54:01
183
转载 Bit Manipulation
常用位操作符有:For JAVA:运算符优先级为从上到下递减,但>,>>>优先级相同。操作符功能用法~位求反~expr左移expr1 >>带符号右移,左边空出的位以原来最左边的0或者1填充expr1 >> expr2>>>
2017-09-29 03:16:38
186
转载 JAVA "Public", "Protected", "Private" and "Friendly"的区别--笔记
1、public:public表明该数据成员、成员函数是对所有用户开放的,所有用户都可直接进行调用 2、protected:protected对于子类来说,就是public的,没有任何限制,而对于其他的外部class,protected就变成private。 3、private:private表示私有的意思。除class自己外,任何人都不可以直接使用,即便是子类都不可以使用。
2017-09-29 00:07:04
203
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