Joeyonng
Notebook
Pages
About
Backyard
Machine Learning
40
Multi-layer Perceptron
Welcome
Notations and Facts
Linear Algebra
1
Fields and Spaces
2
Vectors and Matrices
3
Span and Linear Independence
4
Basis and Dimension
5
Linear Map and Rank
6
Inner Product and Norm
7
Orthogonality and Unitary Matrix
8
Complementary Subspaces and Projection
9
Orthogonal Complement and Decomposition
10
SVD and Pseudoinverse
11
Orthogonal and Affine Projection
12
Determinants and Eigensystems
13
Similarity and Diagonalization
14
Normal and Hermitian Matrices
15
Positive Definite Matrices
Calculus
16
Derivatives
17
Chain rule
Probability and Statistics
18
Probability
19
Random Variables
20
Expectation
21
Common Distributions
22
Moment Generating Function
23
Concentration Inequalities I
24
Convergence
25
Limit Theorems
26
Maximum Likelihood Estimation
27
Bayesian Estimation
28
Expectation-maximization
29
Concentration Inequalities II
Learning Theory
30
Statistical Learning
31
Bayesian Classifier
32
Effective Class Size
33
Empirical Risk Minimization
34
Uniform Convergence
35
PAC Learning
36
Rademacher Complexity
Machine Learning
37
Linear Discriminant
38
Perceptron
39
Logistic Regression
40
Multi-layer Perceptron
41
Boosting
42
Support Vector Machine
43
Decision Tree
44
Principle Component Analysis
Deep Learning
45
Transformer
Table of contents
Preliminary
Calculus
Supervised Learning
Backpropagation
Machine Learning
40
Multi-layer Perceptron
40
Multi-layer Perceptron
Preliminary
Calculus
Chain Rule
?sec-chain-rule
Supervised Learning
Perceptron
Chapter 38
Logistic Regression
Chapter 39
Backpropagation
39
Logistic Regression
41
Boosting