- 博客(23)
- 收藏
- 关注
原创 Notebook
计算图的概念import tensorflow as tfa = tf.constant([1.0,2.0],name = "a")b = tf.constant([2.0,3.0],name = "b")result = a + b#通过a.graph可以查看张量所属的计算图。因为没有特定指定,所以这个计算图应该等于#当前默认的计算图。所以下面这个操作输出值为Trueprint(a...
2019-12-18 21:55:29
430
原创 Notebook
计算图的概念import tensorflow as tfa = tf.constant([1.0,2.0],name = "a")b = tf.constant([2.0,3.0],name = "b")result = a + b#通过a.graph可以查看张量所属的计算图。因为没有特定指定,所以这个计算图应该等于#当前默认的计算图。所以下面这个操作输出值为Trueprint(a...
2019-12-17 21:10:29
354
原创 深度学习——损失函数
深度学习——损失函数之前由于个人懒惰的发了篇极差的文章,现在更正错误,发一篇正在学习tensorflow的笔记在构建神经网络过程中,为了刻画神经网络模型的效果以及优化目标,需要使用到损失函数(loss function)什么是损失函数所谓损失函数使用来估计模型预测值与实际值的不一样程度,是一个绝对值,损失函数越小,模型的拟合度越好。在之前的机械学习过程中,学过代价函数(cost func...
2019-10-28 15:40:58
767
原创 数字图像处理:边缘检测(Edge detection)
数字图像处理:边缘检测(Edge detection)测试编译器为MATLAB作为入门计算机视觉领域来说,Matlab是款非常使用的初学工具,其中的边缘检测、图像分割、霍夫变换等经典技术依然活跃在计算机视觉很多领域。因此,学好数字图像处理是我们入门计算机领域一个非常好的途径,好了话不多说,来和笔者一起看一下今天的主题-边缘检测。一.What is Digital Image Processi...
2019-10-25 16:26:33
3094
原创 Untitled
项目概述数据统计用图显示具有说服力农业前景目标市场潜在竞争者仍较少商业模式盈利模式预测流量变现广告商入驻物联网一体化盈利图像表示未来展望短期市场信息大规模市场调查管理模式提供内部算法与大型企业合作经营?系统设计与架构升级,版本更新,内容更新物联网一体化开展畜牧兽医行业的扩展核心产品与服务项目背景时代背景市场背景(解决农户的迫切需求)开发...
2019-10-15 13:26:21
214
原创 ex6_spam使用SVM进行垃圾邮件分类
Exercise 6 | Spam Classification with SVMs%% Instructions% ------------% % This file contains code that helps you get started on the% exercise. You will need to complete the following functi...
2019-10-14 20:43:54
712
原创 ex6支持向量机
Exercise 6 | Support Vector Machines%% Machine Learning Online Class% Exercise 6 | Support Vector Machines%% Instructions% ------------% % This file contains code that helps you get started...
2019-10-14 20:29:46
138
原创 ex5逻辑线性回归和方差和偏差
Exercise 5 | Regularized Linear Regression and Bias-Variance%% Instructions% ------------% % This file contains code that helps you get started on the% exercise. You will need to complete th...
2019-10-14 20:29:22
254
原创 ex4神经网络学习
ex4神经网络学习% Machine Learning Online Class - Exercise 4 Neural Network Learning% Instructions% ------------% % This file contains code that helps you get started on the% linear exercise. You...
2019-10-11 21:18:46
438
原创 ex3_nn神经网络
ex3-nn 神经网络%% Machine Learning Online Class - Exercise 3 | Part 2: Neural Networks% Instructions% ------------% % This file contains code that helps you get started on the% linear exercise....
2019-10-11 20:52:53
126
原创 ex3多类别分类和神经网络
ex3多类别分类和神经网络%% Machine Learning Online Class - Exercise 3 | Part 1: One-vs-all% Instructions% ------------%% This file contains code that helps you get started on the% linear exercise. You...
2019-10-11 20:50:16
157
原创 ex2_reg逻辑回归
ex2_reg%% Initializationclear ;close all; clc%% Machine Learning Online Class - Exercise 2: Logistic Regression%% Instructions% ------------%% This file contains code that helps you get st...
2019-10-11 20:26:28
185
原创 ex2
ex2.m%% Machine Learning Online Class - Exercise 2: Logistic Regression%% Instructions% ------------% % This file contains code that helps you get started on the logistic% regression exerci...
2019-10-11 17:34:01
147
原创 ex1_multi
Part 1:Feature Normalization%% Clear and Close Figuresclear ; close all; clcfprintf('Loading data ...\n');%% Load Datadata = load('ex1data2.txt');X = data(:, 1:2);y = data(:, 3);m = length(y...
2019-10-11 17:20:48
185
原创 Deep_Learning AndrewNg_course Implement ex1
ex1(1)Part 1: Basic Function% Complete warmUpExercise.mfprintf('Running warmUpExercise ... \n');fprintf('5x5 Identity Matrix: \n');warmUpExercise()fprintf('Program paused. Press enter to contin...
2019-10-11 17:07:09
73
原创 9.25爬虫篇(1)
Python3 网络爬虫页面种类:1. 静态页面;2. 动态页面网址URL审查元素:F12# -*- coding:UTF-8 -*-import requestsif __name__ == '__main__': target = 'http://www.biqukan.com/1_1094/5403177.html' #target 目标...
2019-09-28 13:26:53
98
原创 9.26Dimensionality Reduction(降维)
Dimensionality Reduction(降维)Motivation I:Data Compression 数据压缩take less memory and disk, speed up our learning algorithmsMotivation II: Data Visualization(数据可视化)when you are trouble in too many d...
2019-09-26 21:29:26
152
原创 9.26无监督学习unsupervised learning algorithm
Clustering(聚类算法)Unsupervised learning introductionsupervised learning problem in case is given a set of labels to fit a hypothesis to it.K-means algorithm(K均值)coherent subsets子集coherent clust...
2019-09-26 17:15:15
296
原创 9.25机械学习系统的设计、支持向量机
Machine learning system designPrioritizing what to work on: Spam classification exampleHow to spend your time to make it have low error?Collect lots of dataDevelop sophisticated features based on...
2019-09-24 22:15:32
196
原创 9.24(2)
Model selectiond=degree.of.polynomidd = degree .of .polynomidd=degree.of.polynomidd=1,hθ(x)=θ0+θ1xd=1,h_{\theta}(x)=\theta_0 +\theta_1xd=1,hθ(x)=θ0+θ1xd=2,hθ(x)=θ0+θ1x+θ2xd=2,h_{\theta}(x)=\thet...
2019-09-24 21:53:28
74
原创 9.23
Backpropagation algorithmwe taking about trying to minimize the cost function.Gradient computionJ(Θ)=−1/m[∑i=1mJ{(\Theta)} = -1/m [ \displaystyle \sum^{m}_{i=1}J(Θ)=−1/m[i=1∑m∑k=1Ky(k)\displaysty...
2019-09-23 16:09:41
104
原创 9.22(2)
cost functionNeural Network(Classification){(x(1)x^{(1)}x(1),y(1)y^{(1)}y(1)),(x(2)x^{(2)}x(2),y(2)y^{(2)}y(2)),…,(x(m)x^{(m)}x(m),y(m)y^{(m)}y(m))}L=L =L=total no, of layers in networksls_lsl=n...
2019-09-22 22:04:30
65
原创 9.21(real version)
non-linear hypotheses非线性假设to understand why we need non-linear hypotheses (非线性假设),Neurons and the brainNeural Networks are a pretty old algorithm that was originally motivated by the goal of havin...
2019-09-22 16:05:54
121
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