Machine Learning Math

The main branches of mathematics involved in machine learning include linear algebra, linear functions, linear graphics, probability and statistics. Behind every machine learning success there is mathematics as all machine learning models are constructed using solutions and ideas from math. The purpose of the ML is to create models for understanding thinking. 

Linear Functions

In regards to the mathematical concepts, linear mean straight where a linear function refers to a straight line and a linear graph represents a linear function 

(Insert Image)

Linear Algebra

Linear algebra is the foundation of data science as a comprehensive knowledge of linear algebra enhances one’s capability in understanding data science algorithms some examples can be seen below:

(Insert image )

Probability

Probability refers to the likelihood that an event will occur or how likely something might be true.

For instance, an individual may have 6 balls in a bag: 3 red, 2 green, and 1 blue

If the individual is blindfolded, what is the probability that he or she will pick a green ball?

There are only two occurrences of green balls as there are only 2 balls out of a possible 6 balls. Therefore, the probability of picking a green ball is 2 out of 6. This in fractional form can be represented as  2/6 which is 0.33333…

Consequently, finding the probability of an outcome can be obtained by the formula below:

Probability = Ways / Outcomes

(insert image )

Statistics

Statistics refers to the ability to collect, analyze, interpret as well as present data. When handling statistics it is vital to ask questions such as what is the most common? What is expected? What is the most normal

Below illustrates a graphical representation of statistical data.