MaiMaiMai
Course InfoChaptersResourcesWork

Course Chapters

00
Linear Regression
01
Basics of Probability
02
Discrete Random Variables
03
Probability Densities
04
Functions of Multiple Variables
05
Partial Derivatives
06
Chain Rule
07
Directional Derivatives
08
Differentials and Jacobians
09
Optimization
10
Multivariate Integration
11
Multivariate Gaussian Distribution
12
Transformations of Densities
13
One layer Neural Networks
14
Deep Neural Networks

Probability

Basics of Probability

Addition and multiplication rules, conditional probability, and Bayes' theorem.

Discrete Random Variables

Bernoulli, Binomial, Poisson, Categorical and Multinomial distributions.

Probability Densities

Gaussian, Uniform, Exponential distributions. Transformation of densities.

Multivariate Gaussian Distribution

Conditionals, marginals, Bayes updates, maximum likelihood estimation

Transformations of Densities

Change of variables, Jacobians.

Multivariate Calculus

Functions of Multiple Variables

Graphical representations of multivariate functions. Limits and continuity

Partial Derivatives

Understanding change in multiple dimensions.

Chain Rule

Generalizing the chain rule for multivariate functions.

Directional Derivatives

Rates of change in any direction. Opimal direction of change.

Differentials and Jacobians

Linear approximations, differentials, and Jacobians.

Optimization

Optimization of multivariate functions.

Multivariate Integration

Integration of multivariate functions.

Machine Learning

Linear Regression

Predicting continuous values using curve fitting techniques.

One layer Neural Networks

Categorizing data into distinct classes using logistic regression and other classifiers.

Deep Neural Networks

Building complex models inspired by the human brain.