The Basics of Machine Learning

If you read all those books and looked a little bit around the internet you would probably be able to know what is machine learning but for me, I like the Arthur Samuel definition: “ A field of study that gives computers the ability to learn without being explicitly programmed”, In summary, machine learning is a sub-field of artificial intelligence, where we design systems that can learn from a provided data by training it.

There are 4 types of machine learning but two of them are the most used, Supervised, and unsupervised learning.

It is basically when you know the output so working with a set of labeled data, let’s say a classic example is to classify email messages into spam and non-spam you basically feed the algorithm with the input and the output and based on it the algorithm would eventually predict a class out of a never seen data based on experience.

The most used supervised algorithms are:

On the other hand, you have unsupervised learning, in which you let the algorithm learn on its own, formally let the algorithm find a hidden pattern in a load of data, there is no right or wrong answer, you are just training it and looking for the patterns it generates.

Unsupervised learning algorithms apply the following techniques to describe the data:

You would eventually come across two other types of machine learning That are getting more and more attention, read carefully.

The most used algorithms are:

The dataset contains both labeled and unlabeled examples. Usually, the quantity of unlabeled examples is much higher than the number of labeled examples. The goal of a semi-supervised learning algorithm is the same as the goal of the supervised learning algorithm.

A subfield of machine learning where the machine “lives” in an environment and is capable of perceiving the state of that environment as a vector of features. The machine can execute actions in every state. Different actions bring different rewards and could also move the machine to another state of the environment. The goal of a reinforcement learning algorithm is to learn a policy. A policy is a function f(similar to the model in supervised learning) that takes the feature vector of a state as input and outputs an optimal action to execute in that state. The action is optimal if it maximizes the expected average reward.

The most used algorithms are:

Python is becoming more and more popular because of plenty of reasons. It is even considered that it is mandatory to master the Python syntax before doing anything interesting like data science. Though there are plenty of reasons to learn Python, one of the key reasons is that it is the best language to master if you want to analyze the data or get into the field of data analysis and data sciences. In order to start your data science journey, you will have to first learn the bare minimum syntax. After that, you would have to focus on developing structured projects. Then, you may want to start developing your very own, free-form projects.

Over 83% of the almost 24,000 data professionals used Python, use python on a daily basis.

R is an integrated suite of software facilities for data manipulation, calculation, and graphical display. It includes

SQL (Structured Query Language) is a domain-specific language used in programming and designed for organizing data held in a relational database Management system. As the job of a Data Scientist is to transform raw data into significant bits of knowledge, hence they essentially use SQL for data recovery. To be a powerful data Scientist, they should know how to wrangle and concentrate data from the databases utilizing SQL language.

If you are just about to start with your machine learning and want to learn from scratch, I will be making this series that would be 5–6 minutes long on machine learning and some side projects at the end of every chapter so stay tuned and happy learning

Those are my personal research, if you have any comments please reach out to me.

Welcome to my medium page