- 博客(7)
- 问答 (1)
- 收藏
- 关注
RSS订阅原创 Deep Learning by Andrew Ng --- Sparse coding
稀疏编码介绍稀疏编码算法是一种无监督学习方法，它用来寻找一组“超完备”基向量来更高效地表示样本数据。稀疏编码算法的目的就是找到一组基向量 ϕi\begin{align}\mathbf{\phi}_i\end{align} ，使得我们能将输入向量 x 表示为这些基向量的线性组合： x=∑i=1kaiϕi\begin{align}\mathbf{x} = \sum_{i=1}^k a_i \math
2015-04-18 16:41:29
1442
原创 Deep learning by Andrew Ng --- Linear Decoder
Sparse Autoencoder Recap:Because we used a sigmoid activation function for f(z(3)), we needed to constrain or scale the inputs to be in the range [0,1], since the sigmoid function outputs numbers in th
2015-04-10 16:31:37
1326
原创 Deep Learning by Andrew Ng --- stacked autoencoder
When should we use fine-tuning?It is typically used only if you have a large labeled training set; in this setting, fine-tuning can significantly improve the performance of your classifier. However, if
2015-04-08 20:05:04
2688
1
原创 Deep Learning by Andrew Ng --- self-taught
本次UFLDL练习大致流程：通过对标记为5-9的数字图像进行self-taught特征提取（笔画特征），获得特征参数opttheta。use opttheta to obtain a（2） which represente the labeled input data.Training and testing the logistic regression model(with softmax
2015-04-06 21:17:29
1192
原创 python --- 多线程之threading
join函数join()会等到调用了该函数的线程执行完后再去执行接下来的代码。比如：import threadingfrom time import ctime ,sleeploops = [2,4]def loop(nloop , nsce): print 'start loop:',nloop,'at:',ctime() sleep(nsce) print 'loop:
2015-04-05 19:31:35
859
原创 Deep Learning by Andrew Ng --- Softmax regression
这是UFLDL的编程练习。Weight decay（Softmax 回归有一个不寻常的特点：它有一个“冗余”的参数集）后的cost function和梯度函数：cost function：J(θ)=−1m⎡⎣∑i=1m∑j=1k1{y(i)=j}logeθTjx(i)∑kl=1eθTlx(i)⎤⎦+λ2∑i=1k∑j=0nθ2ij\begin{align}J(\theta) = - \frac{
2015-04-04 15:52:16
1696
原创 Deep Learning by Andrew Ng --- PCA and whitening
这是UFLDL的编程练习。具体教程参照官网。PCAPCA will find the priciple direction and the secodary direction in 2-dimention examples. then x~(i)=x(i)rot,1=uT1x(i)∈R.\begin{align}\tilde{x}^{(i)} = x_{{\rm rot},1}^{(i)}
2015-04-02 21:00:32
1071
空空如也
Adroid Studio无法找到maven_push.gradle文件
2015-01-23
TA创建的收藏夹 TA关注的收藏夹
TA关注的人