• 投稿

Mathematics for Machine Learning (Coursera, Imperial college of London 完整版)

4.4万
103
2018-04-09 06:54:00
601
278
3830
219
转自https://www.coursera.org/specializations/mathematics-machine-learning by Imperial College of London and Coursera David Dye, Professor of Metallurgy Samuel J. Cooper, Lecturer A. Freddie Page, Strategic Teaching Fellow
线性代数
微积分
机器学习
PCA
math4ML
深度碎片 发消息
As Simple As Possible
视频选集
（1/110）
introduction solving data science challenges with math
05:54
motivation for linear algebra
03:30
getting a handle on vectors
09:06
operations with vectors
11:29
week1 summary
01:05
Introduction to module2 vectors
00:50
modulus and inner product
09:34
cosine and dot product
05:53
projection
06:48
changing basis
11:25
basis, vector space, linear independence
04:19
applications of changing basis
03:29
summary week 2
01:20
matrices, vectors, soliving simultaneous equations
05:32
how matrices transform space
05:42
types of matrix transformation
08:39
composition or combination of matrix transformations
07:50
solving apples banana problem gaussian elimination
08:01
going from gaussian elimination to finding the inverse matrix
08:38
determinants and inverses
12:49
summary
00:59
introduction Einstein summation convention and symmetry of dot product
09:54
doing a transformation in a changed basis
06:31
matrices changing basis
11:15
orthogonal matrices
08:13
the Gram Smchidt process
06:08
Example reflecting in a plane
14:11
welcome to module 5
00:34
what are eigenvalues and eigenvectors
04:25
special eigen cases
03:32
calculating eigenvectors
10:07
changing to eigenbasis
05:52
eigenbasis example
07:26
pagerank
08:44
wrap up
02:47
summary
01:15
welcome to multivariate calculus
01:41
welcome to module 1
01:05
functions
04:18
rise over run
04:57
definition of a derivative
10:43
differentiation examples and special cases
07:49
product rule
04:08
chain rule
05:23
taming a best
05:39
see you next module
00:40
welcome to Module 2
01:04
variables, constants and context
07:57
differentiate with respect to anything
04:44
the jacobian
05:50
Jacobian applied
06:23
the sandpit
04:43
the hessian
05:39
reality is hard
04:37
see you next module
00:24
welcome to module 3
00:36
multivariate chain rule
02:39
more multivariate chain rule
05:39
simple neural networks
05:52
more simple neural networks
04:12
see you next module
00:34
welcome to module 4
00:36
building approximate functions
03:28
power series
03:38
power series derivation
09:09
power series details
06:14
examples
05:20
linearisation
05:17
multivariate taylor
06:27
see you next module
00:28
welcome to module 5
08:15
gradient descent
09:07
constrained optimization
08:35
see you next module
02:08
simple linear regression
10:12
general non linear least squares
07:13
doing least squares regression analysis in practice
06:19
wrap up of this course
00:36
Introduction to the course
03:47
welcome to module 1
00:42
mean of a dataset
04:00
variance of one dimensional datasets
04:55
variance of higher dimensional datasets
05:17
effect on the mean
04:46
effect on the covariance
03:31
see you next module
00:27
welcome to module 2
01:48
dot product
04:44
inner product definition
05:03
inner product length of vectors
04:44
inner product distances between vectors
03:42
inner product angles and orthogonality
05:42
Inner products of functions and random variables (optional)
07:23
heading to next module
00:36
welcome to module 3
00:41
projection onto 1D subspaces
07:43
Example projection onto 1D subspaces
03:26
projections onto higher dimensional subspaces
08:33
example projection onto a 2D subspace
03:52
this is module 3
00:33
welcome to module 4
01:09
problem setting and PCA objective
07:46
finding the coordinates of the projected data
05:29
reformulation of the objective
10:26
finding the basis vectors that span the principle subspaces
07:40
steps of PCA
04:08
PCA in high dimensions
05:49
other interpretations of PCA
07:42
summary of this module
00:43
this was the course on PCA
00:57

图解机器学习的数学直觉：线性代数，微积分，PCA（全完结）
深度碎片
11.5万 292

吴恩达机器学习图解笔记
深度碎片
9.8万 285

Santa Fe Institute 复杂系统公开课Complexity: An introduction
深度碎片
2.1万 35

人人必备的数学思维Mathematical thinking by Stanford University and Coursera
深度碎片
2.9万 45

李宏毅深度学习课程（全2课2017年版）笔记汇总
深度碎片
3万 98

图解CNN论文：尝试用最少的数学读懂深度学习论文
深度碎片
4.6万 54

Economics of Money and Banking (coursera)
深度碎片
1.9万 48

阿姆斯特丹大学统计课基础版Basic Statistics by University of Amsterdam and Coursera
深度碎片
1.2万 124

献给所有认为数学和深度学习很重要，但认为自己“不擅长数学”的人！
深度碎片
2.3万 20

图解吴恩达机器学习（2019直觉版）持续更新
深度碎片
1.2万 6

吴恩达第五课RNN笔记
深度碎片
3.2万 127

图解教材:概率机器学习（Murphy)
深度碎片
1.3万 2

探索一句话版的机器学习与深度学习
深度碎片
1.2万 10

图解教材: 模式识别与机器学习（Bishop)
深度碎片
2万 12

概率机器学习基础：MIT概率课图解笔记
深度碎片
1.8万 8

fast.ai 2019 课程（人工中文翻译进行中）
深度碎片
1.4万 26

哈佛通识概率普及课（特别推荐）Fat Chance: Probability from the Ground Up by Harvard and Edx
深度碎片
1.2万 28

哈佛大学最受欢迎的统计课Harvard Statistics 110 introduction
深度碎片
1.6万 1

mismanagement_genius_hypothesis
深度碎片
269 0

make a blog talk
深度碎片
223 0
展开
用AI为孩子创作优质内容
客服
顶部
赛事库 课堂 2021拜年纪