- 博客(14)
- 收藏
- 关注
原创 RNN-递归神经网络
pLearning continuous phrase representations and syntactic parsing with Recursive Neural Networks.pdf
2014-06-09 21:55:23 2042
原创 K-means(tri)利用三角不等式性质加速k-means
paper:Using the Triangle Inequality to Accelerate k-means公式1:x
2014-06-09 10:43:52 3699 1
原创 softmax
softmax是柔性化最大值,是一种归一操作,使得输出在(0,1)之间。举例来说a=3,b=6,c=9. max=9,softmax=9/(3+6+9)=0.5,argmax其实是取得max时的arg,argmax=c
2014-06-08 15:46:05 4534
原创 Using the Triangle Inequality to Accelerate k-Means
If a point is far away from a center, it is not necessary to calculate the exact distance between the point and the center.如果一个点距离中心很远,那么计算这个d
2014-06-01 22:10:46 877
转载 Efficient Estimation of Word Representations in Vector Space
标题:Efficient Estimation of Word Representations in Vector Space作者:Tomas Mikolov发表于:ICLR 2013
2014-06-01 12:21:05 1485
原创 An Analysis of Single-Layer Networks in Unsupervised Feature Learning
K-means:http://metaoptimize.com/qa/questions/4964/why-does-k-means-generate-such-good-features-especially-compared-to-gmmIn the paper above, Ng's group uses K-means for dictionary learning; that
2014-06-01 12:15:45 1123
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