zealscott
码龄7年
关注
提问 私信
  • 博客：728,471
    728,471
    总访问量
  • 196
    原创
  • 1,378,154
    排名
  • 326
    粉丝
  • 2
    铁粉

个人简介：https://tech.zealscott.com

IP属地以运营商信息为准，境内显示到省（区、市），境外显示到国家（地区）
IP 属地：浙江省
  • 加入CSDN时间： 2017-12-14
博客简介：

crazy_scott的博客

查看详细资料
个人成就
  • 获得407次点赞
  • 内容获得119次评论
  • 获得1,796次收藏
  • 代码片获得1,628次分享
创作历程
  • 3篇
    2021年
  • 22篇
    2020年
  • 29篇
    2019年
  • 142篇
    2018年
成就勋章
TA的专栏
  • CMU 11-785
    22篇
  • 凸优化--机器学习数学基础
    9篇
  • 数据科学的线性代数基础
    19篇
  • OperatingSystem
    19篇
  • linear algebra
    19篇
  • 刷题
    16篇
  • 树莓派
    4篇
  • hexo
    4篇
  • 工具使用
    9篇
  • 数据结构
    4篇
  • debug
    8篇
  • apue
    1篇
  • 神经网络
    7篇
  • DistributionSystem
    32篇
  • PGM
  • MachineLearning
    16篇
  • 凸优化
    9篇
  • Web
    1篇
  • Database
    19篇
  • Statistics
    1篇
  • 数据库系统实现
    5篇
  • PUlearning
    3篇
创作活动更多

新星杯·14天创作挑战营·第9期

这是一个以写作博客为目的的创作活动，旨在鼓励大学生博主们挖掘自己的创作潜能，展现自己的写作才华。如果你是一位热爱写作的、想要展现自己创作才华的小伙伴，那么，快来参加吧！我们一起发掘写作的魅力，书写出属于我们的故事。我们诚挚邀请你们参加为期14天的创作挑战赛！ 注： 1、参赛者可以进入活动群进行交流、分享创作心得，互相鼓励与支持（开卷），答疑及活动群请见 https://bbs.csdn.net/topics/619626357 2、文章质量分查询：https://www.csdn.net/qc

473人参与 去参加
  • 最近
  • 文章
  • 代码仓
  • 资源
  • 问答
  • 帖子
  • 视频
  • 课程
  • 关注/订阅/互动
  • 收藏
搜TA的内容
搜索 取消

CMU 11-785 L23 Variational Autoencoders

EM for PCAWith complete informationIf we knew zzz for each xxx, estimating AAA and DDD would be simplex=Az+Ex=A z+E x=Az+EP(x∣z)=N(Az,D)P(x \mid z)=N(A z, D)P(x∣z)=N(Az,D)Given complete information (x1,z1),(x2,z2)\left(x_{1}, z_{1}\right),\lef
原创
发布博客 2021.03.08 ·
381 阅读 ·
1 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L22 Revisiting EM algorithm and generative models

Key pointsEM: An iterative technique to estimate probability models for data with missing components or informationBy iteratively “completing” the data and reestimating parametersPCA: Is actually a generative model for Gaussian dataData lie close
原创
发布博客 2021.02.25 ·
478 阅读 ·
1 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L21 Boltzmann machines2

The Hopfield net as a distributionThe Helmholtz Free Energy of a SystemAt any time, the probability of finding the system in state sss at temperature TTT is PT(s)P_T(s)PT​(s)At each state it has a potential energy EsE_sEs​The internal energy of t
原创
发布博客 2021.01.21 ·
429 阅读 ·
1 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L20 Boltzmann machines 1

Training hopfield netsGeometric approachW=YYT−NpI\mathbf{W}=\mathbf{Y} \mathbf{Y}^{T}-N_{p} \mathbf{I}W=YYT−Np​IE(y)=yTWy\mathbf{E}(\mathbf{y})=\mathbf{y}^{T} \mathbf{W y}E(y)=yTWySine : yT(YYT−NpI)y=yTYYTy−NNp\mathbf{y}^{T}\left(\mathbf{Y} \mat
原创
发布博客 2020.12.16 ·
238 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L19 Hopfield network

Hopfield NetSo far, neural networks for computation are all feedforward structuresLoopy networkEach neuron is a perceptron with +1/-1 outputEvery neuron receives input from every other neuronEvery neuron outputs signals to every other neuron
原创
发布博客 2020.11.07 ·
246 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L18 Representation

Logistic regressionThis the perceptron with a sigmoid activationIt actually computes the probability that the input belongs to class 1Decision boundaries may be obtained by comparing the probability to a thresholdThese boundaries will be lines (hype
原创
发布博客 2020.11.07 ·
157 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L17 Seq2seq and attention model

Generating LanguageSynthesisInput: symbols as one-hot vectorsDimensionality of the vector is the size of the 「vocabulary」Projected down to lower-dimensional “embeddings”The hidden units are (one or more layers of) LSTM unitsOutput at each time:
原创
发布博客 2020.08.06 ·
276 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L16 Connectionist Temporal Classification

Sequence to sequenceSequence goes in, sequence comes outNo notion of “time synchrony” between input and outputMay even nots maintain order of symbols (from one language to another)With order synchronyThe input and output sequences happen in the
原创
发布博客 2020.08.06 ·
273 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L15 Divergence of RNN

Variants on recurrent netsArchitecturesHow to train recurrent networks of different architecturesSynchronyThe target output is time-synchronous with the inputThe target output is order-synchronous, but not time synchronousOne to oneNo rec
原创
发布博客 2020.05.30 ·
431 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L14 Stability analysis and LSTMs

StabilityWill this necessarily be「Bounded Input Bounded Output」?Guaranteed if output and hidden activations are boundedBut will it saturate？Analyzing RecursionSufficient to analyze the behavior of the hidden layer since it carries the relevant
原创
发布博客 2020.05.25 ·
509 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L13 Recurrent Networks

Modelling SeriesIn many situations one must consider a series of inputs to produce an outputOutputs too may be a seriesFinite response modelCan use convolutional neural net applied to series data (slide)Also called a Time-Delay neural network
原创
发布博客 2020.05.20 ·
326 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L12 Back propagation through a CNN

ConvolutionEach position in zzz consists of convolution result in previous mapWay for shrinking the mapsStride greater than 1Downsampling (not necessary)Typically performed with strides > 1PoolingMaxpoolingNote: keep tracking of loc
原创
发布博客 2020.05.19 ·
426 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L10 CNN architecture

ArchitectureA convolutional neural network comprises “convolutional” and “downsampling ” layersConvolutional layers comprise neurons that scan their input for patternsDownsampling layers perform max operations on groups of outputs from the convolutio
原创
发布博客 2020.05.19 ·
234 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L09 Cascade-Correlation and Deep Learning

Cascade-Correlation AlgorithmStart with direct I/O connections only. No hidden units.Train output-layer weights using BP or Quickprop.If error is now acceptable, quit.Else, Create one new hidden unit offline.Create a pool of candidate units. Each ge
原创
发布博客 2020.05.19 ·
297 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L08 Motivation of CNN

MovivationFind a word in a signal of find a item in pictureThe need for shift invarianceThe location of a pattern is not importantSo we can scan with a same MLP for the patternJust one giant...
原创
发布博客 2020.05.07 ·
217 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

Nodejs 豆瓣爬虫实践

使用 Nodejs 从豆瓣小组中爬取帖子，并进行过滤。前端网页解析网页结构打开一个豆瓣小组网页，例如https://www.douban.com/group/16473/使用 F12 解析网站，可以看到，每一个帖子都由一个a标签构成，标题为title我们需要提取的包括标题、URL以及时间信息，因此可以直接使用request以及cheerio包进行提取：request(opt, f...
原创
发布博客 2020.05.07 ·
847 阅读 ·
1 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L07 Optimizers and regularizers

OptimizersMomentum and Nestorov’s method improve convergence by normalizing the mean (first moment) of the derivativesConsidering the second momentsRMS Prop / Adagrad / AdaDelta / ADAM1Simple ...
原创
发布博客 2020.05.03 ·
224 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L06 Optimization

ProblemsDecaying learning rates provide googd compromise between escaping poor local minima and convergenceMany of the convergence issues arise because we force the same learning rate on all parame...
原创
发布博客 2020.05.03 ·
319 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

CMU 11-785 L05 Convergence

BackpropagationThe divergence function minimized is only a proxy for classification error(like Softmax)Minimizing divergence may not minimize classification errorDoes not separate the points even...
原创
发布博客 2020.04.23 ·
222 阅读 ·
0 点赞 ·
0 评论 ·
0 收藏

在服务器上部署 Jupyter Notebook

安装 Ananconda使用命令行安装wget wget https://repo.continuum.io/archive/Anaconda3-5.2.0-Linux-x86_64.sh注意，选择安装路径时，如果想要所有用户都能使用，则安装在usr/local/ananconda3目录下注意修改/etc/profile.d下的conda.sh，指定环境变量（在登入另外的用户时会提...
原创
发布博客 2020.04.23 ·
349 阅读 ·
1 点赞 ·
0 评论 ·
2 收藏
加载更多