Machine Learning (ML) and Artificial Intelligence (AI) have not distinction which is universally agreed upon. AI usually condenses on programming computers to make decisions (based on ML models and sets of logical rules) while ML focuses on making predictions about the future.
Both fields are highly interconnected with each other, and, for most non-technical purposes, they are the same.
V. Statistical Model
Instructing a computer to make estimations involves feeding data into machine learning models, which are representations of how the world allegedly works. For instance, if a statistical model is told, which the world works a certain way that taller people make more money than shorter people, then this model can assert who it thinks will make more money, between two person who are 5’22” and 5’9”.
Basically, a model is just a mathematical function, which is a relationship between a set of input and a set of outputs. For example,
f(x) = x²
Given f(x) is a function that takes as input number and returns that number squared. So, f(3) = 9.
Let’s briefly return to the example of the model that predicts income from height. We may assume, that a given human’s annual income is, on average, equal to her/his height times $1.000. So, if someone is 60 inches tall then it’ll be guessed that s/he make $60.000 a year. The model can be represented mathematically as follows:
Income = Height x $1.000
The main point is, machine learning refers to a set of techniques for estimating functions (like income)
based on datasets (heights and associated incomes). These functions are called as models. They can then be used for estimations of future data.
So far, it was explained that statistical models consisted of a mathematical function. These functions are estimated using algorithms. In this context, an algorithm is a predefined set of steps that takes input data and then processes it and gives output consisted of a mathematical function.
VI. Machine Learning Methods
There is two machine learning method that statistical models are constructed.
I. Supervised Learning
Supervised learning is where you have input variables x and an output variable Y and you use an algorithm to learn the mapping function from input to the output.
Y = f(x)
The goal is to approximate the mapping function so well that when you have new input data x that you can predict the output variables Y for that data.
In this method, the process of an algorithm learning from the training dataset can be thought of as a teacher supervising the learning process. The correct answer is known, the algorithm makes predictions on the training data and is corrected by the teacher. Learning process is stopped when the algorithm achieves an acceptable level of performance.
Supervised learning problems can be categorized as regression and classification problems.