- 博客(5)
- 资源 (1)
- 收藏
- 关注
RSS订阅转载 7 Steps for becoming Deep Learning Expert
https://www.linkedin.com/pulse/7-steps-becoming-deep-learning-expert-ankit-agarwalApologies for using Buzz feed like click bait as the title, but it worked and got you to reading this.One of
2015-12-14 09:38:47
744
原创 cs231n 问题
http://cs231n.github.io/linear-classify/， svm classifierHow? if we imagine squashing all those dimensions into only two dimensions, then we can try to visualize what the classifier might be doing:
2015-12-11 08:40:38
1027
转载 debug ipython notebook with breakpoint
http://www.cs.ucl.ac.uk/scipython/notebooks/02-BreakPoints.htmlDebuggingDebugging is the process of finding errors in a programvery important part of programmingcan take considerible timemas
2015-12-08 09:26:36
2094
转载 半正定矩阵
http://www.zybang.com/question/e80011474be291bcaba63134368e3b50.html具有对称矩阵A的二次型f=x’Ax,如果对任何非零向量x,都有x’Ax≥0（或x’Ax≤0）成立,且有非零向量x0,使x0'Ax0=0,则称f为半正定（半负定）二次型,矩阵A称为半正定矩阵（半负定矩阵）.即有定义：设A是实对称矩阵.如果对任意的实非零列矩阵
2015-12-04 09:15:00
2141
原创 终于明白协方差的意义了
协方差代表了两个变量之间的是否同时偏离均值。 如果正相关，这个计算公式，每个样本对（Xi, Yi）, 每个求和项大部分都是正数，即两个同方向偏离各自均值，而不同时偏离的也有，但是少，这样当样本多时，总和结果为正。下面这个图就很直观。下面转载自：http://blog.csdn.net/wuhzossibility/article/details/8087863在概率论中，两
2015-12-03 16:50:03
79728
14
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人