papering - 博客园

2017年9月28日

摘要：阅读全文

posted @ 2017-09-28 23:22 papering 阅读(174) 评论(0) 推荐(0)

Complete space 完备空间与柯西序列巴拿赫空间与完备空间完备空间与和希尔伯特空间封闭closed与完备性complete

摘要： http://www.gatsby.ucl.ac.uk/~gretton/coursefiles/RKHS2013_slides1.pdf RKHS: a function space with a very special structure 阅读全文

posted @ 2017-09-28 21:58 papering 阅读(825) 评论(0) 推荐(1)

a positive definite matrix

摘要： https://en.wikipedia.org/wiki/Definite_quadratic_form https://www.math.utah.edu/~zwick/Classes/Fall2012_2270/Lectures/Lecture33_with_Examples.pdf 阅读全文

posted @ 2017-09-28 20:44 papering 阅读(249) 评论(0) 推荐(0)

The connection between feature spaces and smoothness is not obvious, and is one of the things we’ll discuss in the course.

摘要： http://www.gatsby.ucl.ac.uk/~gretton/coursefiles/lecture4_introToRKHS.pdf 阅读全文

posted @ 2017-09-28 20:29 papering 阅读(123) 评论(0) 推荐(0)

Cauchy sequence Hilbert space 希尔波特空间的柯西序列

摘要： http://mathworld.wolfram.com/HilbertSpace.html A Hilbert space is a vector space with an inner product such that the norm defined by turns into a comp 阅读全文

posted @ 2017-09-28 15:59 papering 阅读(829) 评论(0) 推荐(0)

拓扑量子位

摘要： http://mp.weixin.qq.com/s/hImjVRMHHEC3SAepAoL2Tw 阅读全文

posted @ 2017-09-28 15:50 papering 阅读(190) 评论(0) 推荐(0)

The space of such functions is known as a reproducing kernel Hilbert space.

摘要： Reproducing kernel Hilbert space Mapping the points to a higher dimensional feature space http://www.gatsby.ucl.ac.uk/~gretton/coursefiles/lecture4_in 阅读全文

posted @ 2017-09-28 15:08 papering 阅读(292) 评论(0) 推荐(0)

core action magic number

摘要： core action 阅读全文

posted @ 2017-09-28 12:06 papering 阅读(134) 评论(0) 推荐(0)

辛普森悖论（Simpson's Paradox）

摘要： q 阅读全文

posted @ 2017-09-28 11:49 papering 阅读(240) 评论(0) 推荐(0)

You Can’t Improve What You Can’t Measure

摘要： airlock 阅读全文

posted @ 2017-09-28 11:46 papering 阅读(212) 评论(0) 推荐(0)

2017年9月27日

Latent Activity Trajectory (LAT)

摘要： https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/funcZone_TKDE_Zheng.pdf Specifically, we introduce the concept of Latent Activity 阅读全文

posted @ 2017-09-27 22:24 papering 阅读(177) 评论(0) 推荐(0)

轮廓广告

摘要： http://mp.weixin.qq.com/s/2NoYnwE_FxfhU9qCwH-nnA 用实际轮廓确定商圈的范围阅读全文

posted @ 2017-09-27 21:57 papering 阅读(192) 评论(0) 推荐(0)

Frobenius inner product

摘要： https://en.wikipedia.org/wiki/Frobenius_inner_product Frobenius norm 阅读全文

posted @ 2017-09-27 20:01 papering 阅读(1531) 评论(0) 推荐(0)

Residual (numerical analysis)

摘要： In many cases, the smallness of the residual means that the approximation is close to the solution, i.e., 残差：结果的差值误差：近似解与解的差值 https://en.wikipedia.or 阅读全文

posted @ 2017-09-27 19:51 papering 阅读(425) 评论(0) 推荐(0)

把影响集中到一个点

摘要： http://djt.qq.com/article/view/16 其主要思想就是把影响集中到一个点，然后再发散到一个面，出现意外情况后很容易就回退。 Gmail Labs是一个新特性橱窗，用户可以自己选择一些未正式发布的新特性进行体验，不喜欢可以关闭，在这个过程中，吃了螃蟹，也当了Google的小阅读全文

posted @ 2017-09-27 17:41 papering 阅读(190) 评论(0) 推荐(0)

How to avoid Over-fitting using Regularization?

摘要： http://www.mit.edu/~9.520/scribe-notes/cl7.pdf https://en.wikipedia.org/wiki/Bayesian_interpretation_of_kernel_regularization the degree to which inst 阅读全文

posted @ 2017-09-27 15:58 papering 阅读(252) 评论(0) 推荐(0)

适定性问题

摘要：适定性问题 zh.wikipedia.org/wiki/適定性問題数学术语适定性问题来自于哈达玛所给出的定义。他认为物理现象中的数学模型应该具备下述性质：适定性问题的原型范例包括对于拉普拉斯方程的狄利克雷问题，以及给定初始条件的热传导方程式。在物理过程中解决的这些问题，也许被视为“自然”问题。相阅读全文

posted @ 2017-09-27 15:10 papering 阅读(1647) 评论(0) 推荐(0)

Numerical Differentiation 数值微分

摘要： zh.wikipedia.org/wiki/數值微分数值微分是数值方法中的名词，是用函数的值及其他已知资讯来估计一函数导数的算法。 http://mathworld.wolfram.com/NumericalDifferentiation.html Numerical differentiatio 阅读全文

posted @ 2017-09-27 14:05 papering 阅读(427) 评论(0) 推荐(0)

What Every Computer Scientist Should Know About Floating-Point Arithmetic

摘要： http://docs.oracle.com/cd/E19957-01/806-3568/ncg_goldberg.html 阅读全文

posted @ 2017-09-27 13:55 papering 阅读(201) 评论(0) 推荐(0)

Generally a good method to avoid this is to randomly shuffle the data prior to each epoch of training.

摘要： http://ufldl.stanford.edu/tutorial/supervised/OptimizationStochasticGradientDescent/ 阅读全文

posted @ 2017-09-27 12:08 papering 阅读(158) 评论(0) 推荐(0)

What is the difference between iterations and epochs in Convolution neural networks?

摘要： https://stats.stackexchange.com/questions/164876/tradeoff-batch-size-vs-number-of-iterations-to-train-a-neural-network It has been observed in practic 阅读全文

posted @ 2017-09-27 11:47 papering 阅读(195) 评论(0) 推荐(0)

Every norm is a convex function

摘要： https://ipfs.io/ipfs/QmXoypizjW3WknFiJnKLwHCnL72vedxjQkDDP1mXWo6uco/wiki/Convex_function.html Every norm is a convex function, by the triangle inequal 阅读全文

posted @ 2017-09-27 11:05 papering 阅读(239) 评论(0) 推荐(0)

Moore-Penrose Matrix Inverse 摩尔－彭若斯广义逆埃尔米特矩阵 Hermitian matrix

摘要： http://mathworld.wolfram.com/Moore-PenroseMatrixInverse.html 显然，埃尔米特矩阵主对角线上的元素都是实数的，其特征值也是实数。对于只包含实数元素的矩阵（实矩阵），如果它是对称阵，即所有元素关于主对角线对称，那么它也是埃尔米特矩阵。也就是说，阅读全文

posted @ 2017-09-27 09:14 papering 阅读(1117) 评论(0) 推荐(0)

2017年9月26日

But what exactly do we mean by "gets closer to"?

摘要： https://rdipietro.github.io/friendly-intro-to-cross-entropy-loss/ 【将输入转化为输出：概率分布】 When we develop a model for probabilistic classification, we aim to 阅读全文

posted @ 2017-09-26 21:00 papering 阅读(220) 评论(0) 推荐(0)

information entropy as a measure of the uncertainty in a message while essentially inventing the field of information theory

摘要： https://en.wikipedia.org/wiki/Claude_Shannon In 1948, the promised memorandum appeared as "A Mathematical Theory of Communication," an article in two 阅读全文

posted @ 2017-09-26 19:48 papering 阅读(163) 评论(0) 推荐(0)

SVM vs. Softmax

摘要： http://cs231n.github.io/linear-classify/ 阅读全文

posted @ 2017-09-26 19:23 papering 阅读(158) 评论(0) 推荐(0)

every row of W is a classifier for one of the classes

摘要： every row of W is a classifier for one of the classes As we saw above, every row of W is a classifier for one of the classes. The geometric interpreta 阅读全文

posted @ 2017-09-26 16:18 papering 阅读(206) 评论(0) 推荐(0)

Hinge Loss

摘要： The hinge loss is a convex function, so many of the usual convex optimizers used in machine learning can work with it. It is not differentiable, but h 阅读全文

posted @ 2017-09-26 15:42 papering 阅读(375) 评论(0) 推荐(0)

recognition rate generalization识别率泛化

摘要： http://www1.inf.tu-dresden.de/~ds24/lehre/ml_ws_2013/ml_11_hinge.pdf Two extremes: • Big 𝐶 → the loss is more important → better recognition rate but 阅读全文

posted @ 2017-09-26 15:35 papering 阅读(278) 评论(0) 推荐(0)

polynomial time 图灵机多项式时间

摘要：图灵的基本思想图灵的基本思想是用机器来模拟人们用纸笔进行数学运算的过程，他把这样的过程看作下列两种简单的动作：在纸上写上或擦除某个符号；把注意力从纸的一处移动到另一处；而在每个阶段，人要决定下一步的动作，依赖于（a）此人当前所关注的纸上某个位置的符号和（b）此人当前思维的状态。在可计算性理阅读全文

posted @ 2017-09-26 14:04 papering 阅读(856) 评论(0) 推荐(0)

Conditional random fields

摘要： crf 阅读全文

posted @ 2017-09-26 12:17 papering 阅读(122) 评论(0) 推荐(0)

Frobenius Norm

摘要： http://mathworld.wolfram.com/FrobeniusNorm.html 阅读全文

posted @ 2017-09-26 10:49 papering 阅读(183) 评论(0) 推荐(0)

L2 范数 L1 范数出租车范数

摘要： https://en.wikipedia.org/wiki/Norm_(mathematics) http://cs231n.github.io/classification/ 阅读全文

posted @ 2017-09-26 10:23 papering 阅读(245) 评论(0) 推荐(0)

2017年9月25日

卷积核即滤波器

摘要：输入输出的中间阅读全文

posted @ 2017-09-25 22:43 papering 阅读(189) 评论(0) 推荐(0)

Full卷积 Same卷积 Vaild卷积

摘要：阅读全文

posted @ 2017-09-25 22:03 papering 阅读(410) 评论(0) 推荐(0)

position

摘要： C:\Python36\python.exe D:/pymine/clean/chained_located/chained_located_dynamic_input.py '-69,-47,,,-72,-40,-37,-96,-36,-97,-67,-67,-43,,-100,-70,-54,-62,-92,-98,,-33,-77,-17,-17,,-98,-76... 阅读全文

posted @ 2017-09-25 18:13 papering 阅读(292) 评论(0) 推荐(0)

What happens when we continue stacking deeper layers on a “plain” convolutional neural network?

摘要： http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture9.pdf The deeper model performs worse, but it’s not caused by overfitting! 阅读全文

posted @ 2017-09-25 16:12 papering 阅读(276) 评论(0) 推荐(0)

A vectorized example

摘要： http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture4.pdf 阅读全文

posted @ 2017-09-25 14:19 papering 阅读(130) 评论(0) 推荐(0)

SVM vs. Softmax

摘要： http://cs231n.github.io/linear-classify/ http://cs231n.github.io/assets/svmvssoftmax.png 阅读全文

posted @ 2017-09-25 11:28 papering 阅读(195) 评论(0) 推荐(0)

2017年9月22日

run length encoding

摘要：直观阅读全文

posted @ 2017-09-22 16:16 papering 阅读(126) 评论(0) 推荐(0)