papering - 博客园

2017年9月30日

摘要： https://www.cs.cmu.edu/afs/cs/project/jair/pub/volume4/kaelbling96a-html/node25.html https://www.cs.cmu.edu/afs/cs/project/jair/pub/volume4/kaelbling9 阅读全文

posted @ 2017-09-30 17:29 papering 阅读(204) 评论(0) 推荐(0)

transition_matrix Markov chain

摘要：阅读全文

posted @ 2017-09-30 17:09 papering 阅读(325) 评论(0) 推荐(0)

On Using Very Large Target Vocabulary for Neural Machine Translation Candidate Sampling Sampled Softmax

摘要：【softmax分类器的加速器】 https://www.tensorflow.org/api_docs/python/tf/nn/sampled_softmax_loss This is a faster way to train a softmax classifier over a huge 阅读全文

posted @ 2017-09-30 10:36 papering 阅读(707) 评论(0) 推荐(0)

Brotli

摘要： https://engineering.linkedin.com/blog/2017/05/boosting-site-speed-using-brotli-compression?utm_source=mybridge&utm_medium=web&utm_campaign=read_more 阅读全文

posted @ 2017-09-30 01:08 papering 阅读(205) 评论(0) 推荐(0)

数据到达etl系统的时间晚于事务发生的时间

摘要：迟到阅读全文

posted @ 2017-09-30 00:56 papering 阅读(139) 评论(0) 推荐(0)

事实表维度表从数据仓库角度看数据分析实质

摘要：阅读全文

posted @ 2017-09-30 00:39 papering 阅读(172) 评论(0) 推荐(0)

2017年9月29日

小波分析蒙特卡洛树

摘要：小波蒙特卡洛阅读全文

posted @ 2017-09-29 23:26 papering 阅读(180) 评论(0) 推荐(0)

CNN延拓至复数域

摘要：阅读全文

posted @ 2017-09-29 22:40 papering 阅读(667) 评论(2) 推荐(0)

squared-error loss is much more repaidly updated than mean-absolute-deviation when searching for splits

摘要：平方差损失能较绝对值差损失更快地更新阅读全文

posted @ 2017-09-29 20:37 papering 阅读(328) 评论(0) 推荐(0)

Greedy Function Approximation:A Gradient Boosting Machine

摘要： https://statweb.stanford.edu/~jhf/ftp/trebst.pdf page10 90% to 95% of the observations were often deleted without sacrificing accuracy of theestimates 阅读全文

posted @ 2017-09-29 20:03 papering 阅读(467) 评论(0) 推荐(0)

ridge regression 无惩罚，导致预测结果空间过大而无实用价值

摘要：【 biased regression methods to reduce variance 通过偏回归来减小方差】 https://onlinecourses.science.psu.edu/stat857/node/137 Introducing biased regression method 阅读全文

posted @ 2017-09-29 17:45 papering 阅读(302) 评论(0) 推荐(0)

7 Types of Regression Techniques

摘要： https://www.analyticsvidhya.com/blog/2015/08/comprehensive-guide-regression/ Linear Regression Logistic Regression Polynomial Regression Stepwise Regr 阅读全文

posted @ 2017-09-29 16:39 papering 阅读(361) 评论(0) 推荐(0)

lasso the moon

摘要：阅读全文

posted @ 2017-09-29 16:35 papering 阅读(139) 评论(0) 推荐(0)

Regularization: how complicated the model is? Regularization, measures complexity of model 使预测准确、平稳 predictive stable

摘要： http://www.kdd.org/kdd2016/papers/files/rfp0697-chenAemb.pdf https://homes.cs.washington.edu/~tqchen/pdf/BoostedTree.pdf 【Training Loss measures how w 阅读全文

posted @ 2017-09-29 16:16 papering 阅读(249) 评论(0) 推荐(0)

Bootstrap aggregating Bagging 合奏 Ensemble Neural Network

摘要： zh.wikipedia.org/wiki/Bagging算法 Bagging算法（英语：Bootstrap aggregating，引导聚集算法），又称装袋算法，是机器学习领域的一种团体学习算法。最初由Leo Breiman于1994年提出。Bagging算法可与其他分类、回归算法结合，提高其准阅读全文

posted @ 2017-09-29 14:35 papering 阅读(1464) 评论(0) 推荐(0)

stacked generalization 堆积正则化堆积泛化加权特征线性堆积

摘要： https://en.wikipedia.org/wiki/Ensemble_learning Stacking Stacking (sometimes called stacked generalization) involves training a learning algorithm to 阅读全文

posted @ 2017-09-29 11:52 papering 阅读(498) 评论(0) 推荐(0)

Facebook Gradient boosting 梯度提升 separate the positive and negative labeled points using a single line 梯度提升决策树 Gradient Boosted Decision Trees (GBDT)

摘要： https://www.quora.com/Why-do-people-use-gradient-boosted-decision-trees-to-do-feature-transform Why is linearity/non-linearity important?Most of our c 阅读全文

posted @ 2017-09-29 11:40 papering 阅读(399) 评论(0) 推荐(0)

Channel (digital image) 通道色彩深度 Color_depth

摘要： en.wikipedia.org/wiki/Channel_(digital_image) Color digital images are made of pixels, and pixels are made of combinations of primary colors represent 阅读全文

posted @ 2017-09-29 10:57 papering 阅读(1365) 评论(0) 推荐(0)

顾客去哪家超市

摘要：阅读全文

posted @ 2017-09-29 08:32 papering 阅读(143) 评论(0) 推荐(0)

常返态瞬时态

摘要：阅读全文

posted @ 2017-09-29 08:24 papering 阅读(424) 评论(0) 推荐(0)

马尔科夫链在第n步转移的状态的概率分布

摘要：阅读全文

posted @ 2017-09-29 08:06 papering 阅读(312) 评论(0) 推荐(0)

2017年9月28日

另一视角看世界频域时域傅里叶变换

摘要：视角阅读全文

posted @ 2017-09-28 23:48 papering 阅读(191) 评论(0) 推荐(0)

空间Rm的任意两个范数都互相等价

摘要：阅读全文

posted @ 2017-09-28 23:26 papering 阅读(1072) 评论(0) 推荐(0)

闭方块线度

摘要：阅读全文

posted @ 2017-09-28 23:24 papering 阅读(142) 评论(0) 推荐(0)

连通性保证f具有介值性质

摘要：阅读全文

posted @ 2017-09-28 23:22 papering 阅读(176) 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(835) 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(276) 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(128) 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(851) 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(216) 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(312) 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(138) 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(246) 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(214) 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(182) 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(197) 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(1535) 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(463) 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(201) 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(282) 评论(0) 推荐(0)