daodavid / maths-behind-ml

Maths behind machine learning and some implementations from scratch.

Machine Learning

Maths

• Linear Algebra- in Progress
• Mathematical Analysis - in Progress
• Probability and Statistic - in Progress

ML

From maths to implementations of:

• Linear Regression - in Progress
• Logistic Regression - - in Progress
• Softmax regression
• Priciple Component Analisys

Projects

maths-behind-ml's Issues

Continuous probability

∫f(x)dx= 1.
We reiterate that there are two distinct concepts when talking about distribution.

boostrap-links

https://www.analyticsvidhya.com/blog/2020/02/what-is-bootstrap-sampling-in-statistics-and-machine-learning/

Probability

Loosely speaking,The probability conserns the study of unsertainty.
The probability can be thought of as the fraction of times an event occurs or degree of belief about occurrence of event.We then would like to use the probability to measure a chance of something occurring in an experiment.We often quantify uncertainty in Ml model for uncertainty in predictions produced by the model.Quantifying uncertainty requires the idea of random variable.which is the function that maps outcomes of random experiment to set of properties that we are interested in.Associated with the random variable is a function that measures a particular outcome will occur.This called probability distribution.

issue-0002--covariance-statistic

jupter cs

https://github.com/dunovank/jupyter-themes
jt -t chesterish

issue-0001 : Principle Component analysis --

Understanding and Exploring of Covariance matrix.
How do eigenvalues of covarince matrix give us

Ridge regresion -referenes

https://arxiv.org/pdf/1509.09169.pdf

https://tjzhifei.github.io/links/EMFA.pdf

matrix decompositions

Eingdecompositon.
Singular value decomposition
chelosky decomposition.
Application of decompostions