![](https://img-blog.csdnimg.cn/20201014180756930.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
Machine Learning Self-Learning
文章平均质量分 75
Firehotest
这个作者很懒,什么都没留下…
展开
-
Study Note: Logistic Regression(2)
First of all, let's add something missed from the previous section: What is the practical meaning of output of sigmoid function? It is the posterior possibility of y = 1. P(y=1 |x,Θ) = ? If原创 2016-01-24 12:37:05 · 1256 阅读 · 0 评论 -
Study Note: Logistic Regression(1)
Logistic regression is created for logistic problem. Therefore, the output of such regression should be binary value. Then here is the question, how to create a regression function whose output原创 2016-01-23 20:20:12 · 547 阅读 · 0 评论 -
Study Note: Multiple Variables Regression
How does the bia unit of neural network come out? Let's assume the parameters matrix(vector) is Θ = In order to let variables matrix(vector) is suitable for multiply, we make a extra = 1 f原创 2016-01-23 14:40:57 · 597 阅读 · 0 评论 -
Notes: 线性代数基础回顾
行列式(Determination): 行列式是只针对方阵而言的。 关于行列式,2阶、3阶行列式的求解: 对于三阶行列式的求解: 可以在旁边多加一个同样的以方便看图。 D = 1*2*(-2) + 2*1*(-3)+ (-4)*(-2)*4 - (-4)*2*(-3)- 4 - 8 = -4 + (-6)原创 2016-10-17 09:49:51 · 882 阅读 · 0 评论 -
Self Summary: Back Propagation (BP) network
As we all known, neural network makes use of the back propagation to improve itself. But we need to dig deep to how this runs in this passage. Most of the following content are from http://www.c转载 2016-03-29 11:23:24 · 774 阅读 · 0 评论 -
Self Summary: Lua Language(two useful links) and the difference between : and .
Here is a very useful website about learning Lua: http://tylerneylon.com/a/learn-lua/ Here I just want to talk about the difference of : and . in Lua: Function tablename:fn(...) is the same转载 2016-03-09 10:48:10 · 520 阅读 · 0 评论 -
Self summary: What does typical CNN do and What is Soft-max?
Here is the image stoled from guide of torch: https://github.com/soumith/cvpr2015/blob/master/Deep%20Learning%20with%20Torch.ipynb First, we must know what is convolution. Here is a原创 2016-01-31 17:23:49 · 663 阅读 · 0 评论 -
Study Notes: Lua language for Torch
Lua Data types: Lua has two data structure built-in, a table: {} and tensor(matrix). Also there are Strings, numbers. String use '' : a = 'hello' # is the length operator in Lua转载 2016-01-28 19:05:29 · 1391 阅读 · 0 评论 -
Study Note: About CNN
1/ The difference of CNN and ordinary Neural network Ans: Typical neural network is fully connected network and each unit's activation of this network is: The reason for choosing thi原创 2016-01-15 11:18:35 · 822 阅读 · 0 评论 -
Study Notes of Neural Network Optimization(1)
1/ Things to do before train the network: pre-train the network Normal network pre-training methods include using stacks of RBMs (Restrict Boltzmann Machine); autoencoders and Deep Boltzmann Mach原创 2016-01-21 09:52:36 · 757 阅读 · 0 评论 -
A summary of dropout technique
1/ Motivation: Typically, for overcoming overfitting, we introduce methods like stopping training as soon as performance on a validation set starts to get worse; soft weight sharing[2] and regula原创 2016-01-19 14:28:22 · 785 阅读 · 0 评论 -
A summary about gradient descent
There are three kind of gradient descent now: 1/ Traditional: Like a people who wants to get down of the hill as soon as possible. Then he/she will find a way that has a big steepness of loc原创 2016-01-19 11:03:28 · 879 阅读 · 0 评论