超級推薦!Mathematics for Machine Learning
超級推薦!Mathematics for Machine Learning by Imperial College London and Coursera! 迄今為止,最beginner friendly的為了機器學習定製的高等數學入門課!!!
(帶寬不夠,搬運很辛苦,但是始終無人搬運這部神課程,所以不得不自己搬了!)
Mathematics for Machine Learning (Coursera, Imperial college of London)_嗶哩嗶哩 (゜-゜)つロ 乾杯~-bilibili希望大家能多多受益!
課程視頻與圖解筆記視頻目錄(共三課)
第一課:Linear Algebra for Machine Learning (已完結)
只有含「圖解」的視頻是筆記視頻,其他視頻為原課程視頻
1、introduction solving data science challenges with math
2、motivation for linear algebra
1、圖解學習linear algebra目的:高效求解大量linear equations 2、圖解學習linear algebra目的:高效求解模型參數擬合大量數據 3、圖解線性代數:線代如何切入幫助解決模型優化
3、getting a handle on vectors
4、operations with vectors
5、week1 summary
6、Introduction to module2 vectors
7、modulus and inner product
4、圖解線性代數:向量的本質和加乘運算 5、圖解線性代數:vector length and dot product
8、cosine and dot product
6、圖解線性代數:vector dot product, length, cosine
9、projection
7、圖解線性代數:scalar projection, vector projection 8、圖解線性代數:vector projection 與 vector transformation
10、changing basis
9、圖解線性代數:linear combination, independence, basis vector
11、basis, vector space, linear independence
10、圖解線性代數:vector, projection, basis vector在機器學習中的應用
12、applications of changing basis
13、summary week 2
14、matrices, vectors, soliving simultaneous equations
11、圖解線性代數:matrix簡介
15、how matrices transform space
12、圖解線性代數:用映射projection來理解matrix的變形能力
16、types of matrix transformation
13、圖解線性代數:機器學習的本質與matrix transformation的各種形態
17、composition or combination of matrix transformations
14、圖解線性代數:matrix疊加變形的直觀理解
18、solving apples banana problem gaussian elimination
19、going from gaussian elimination to finding the inverse matrix
15、圖解線性代數:inverse與identity matrix的理解和求解
20、determinants and inverses
16、圖解線性代數:determinant, inverse, dependence, solution
21、summary
22、introduction Einstein summation convention and symmetry of dot product
17、圖解線性代數:einstein summation convention and dot product的對稱性
23、doing a transformation in a changed basis
24、matrices changing basis
25、orthogonal matrices
18、圖解線性代數:我的視野里的vector, basis vector在panda的視野里長得什麼樣子 19、圖解線性代數:案例熊貓與人類的視野轉換 20、圖解線性代數:如何理解orthogonal matrix
26、the Gram Smchidt process
21、圖解線性代數:gram-schmidt與轉換坐標空間來實現vector變形
27、Example reflecting in a plane
28、welcome to module 5
29、what are eigenvalues and eigenvectors
30、special eigen cases
31、calculating eigenvectors
32、changing to eigenbasis
33、eigenbasis example
22、圖解線性代數:eigenvectors and eigenvalues 23、圖解線性代數:eigenvectors and eigenvalues的求解邏輯 24、圖解線性代數:用eigenvector, eigenvalues化簡n個m
34、pagerank
35、wrap up
36、summary
Multivariate Calculus for Machine Learning
37、welcome to multivariate calculus
38、welcome to module 1
39、functions
40、rise over run
41、definition of a derivative
42、differentiation examples and special cases
43、product rule
44、chain rule
45、taming a best
46、see you next module
47、welcome to Module 2
48、variables, constants and context
49、differentiate with respect to anything
50、the jacobian
51、Jacobian applied
52、the sandpit
53、the hessian
54、reality is hard
55、see you next module
56、welcome to module 3
57、multivariate chain rule
58、more multivariate chain rule
59、simple neural networks
60、more simple neural networks
61、see you next module
62、welcome to module 4
63、building approximate functions
64、power series
65、power series derivation
66、power series details
67、examples
68、linearisation
69、multivariate taylor
70、see you next module
71、welcome to module 5
72、gradient descent
73、constrained optimization
74、see you next module
75、simple linear regression
76、general non linear least squares
77、doing least squares regression analysis in practice
78、wrap up of this course
推薦閱讀:
※[PRML學習筆記] CHA 4 Linear Models for Classification
※機器學習入門之邏輯回歸分類
※基於信息瓶頸的空間聚類(一)
※《機器學習實戰》學習總結(十一)——隱馬爾可夫模型(HMM)
※機器學習-各種 Learning 概念簡明介紹
TAG:高等數學 | 機器學習 | 深度學習DeepLearning |