Understanding how Artificial Neural Networks (NNs) work under the hood in simple words. Learn about Feedforward and Back Propagation using intuitive animations.

An Artificial Neural Network (in short just NN) is a computing system that tries to mimic the human brain.
An Artificial Neural Network (in short just NN) is a computing system that tries to mimic the human brain.
Made by Author. An Artificial Neural Network (in short just NN) is a computing system that tries to mimic the human brain.

Intro

I intend to explain it in simple words, so everybody can understand what is going on here.

So, let us begin.

What is NN?

Here is my little animation to visualize the NN structure:


An overview of Machine Learning classification algorithms. The best algorithm and "No free lunch theorem".

A cover photo for the tutorial on Classification Machine Learning algorithms.
A cover photo for the tutorial on Classification Machine Learning algorithms.
Photo by Ian Taylor on Unsplash

Intro

If ML algorithms were a tasty soup, it is still possible to eat it without knowing what is inside. However, I prefer to shed light on the ingredients and the way it was cooked.

We already covered the reasons for learning Machine Learning, went through general terms/definitions, explored which common Python libraries are used for Data Science and ML, and loaded…


A comprehensive guide to starting practicing Machine Learning (ML) in Python for complete beginners with hands-on examples. Learn ML and Upgrade yourself from a complete beginner → to ML practitioner. Explaining the SVM algorithm.

Photo by Kalineri on Unsplash

Intro

The point of SVM is to separate the data into classes by finding a boundary/separator.

In SVM, data points that are on the one side from that separator belong to one class, and those points on the other side belong to another class.

One might wonder: if we want to classify unknown cases why do not use a classification algorithm that works by classifying the data points directly (such as K-Nearest Neighbors) instead of classifying them by separation?

There are…


A step-by-step Exploratory Data Analysis project: from Business problem description to solution and implementation (with code). Using Foursquare API, Beautiful soup, Requests, Pandas, and Folium.

Photo by Irena Carpaccio on Unsplash

Introduction & Summary

The article consists of the following chapters:

  1. Business Problem (Introducing a business idea and my approach to solving it);
  2. Data Analysis (Describing the relevant data and the process…


A comprehensive guide to starting practicing Machine Learning (ML) in Python for complete beginners with hands-on examples. Learn ML and Upgrade yourself from a complete beginner → to ML-practitioner. Explaining the K-NN algorithm.

A cover photo for the article K-Nearest Neighbors. Picture shows Totoro character from the animation “My neighbor Totoro”.
A cover photo for the article K-Nearest Neighbors. Picture shows Totoro character from the animation “My neighbor Totoro”.
Photo by Raychan on Unsplash

Intro

K-NN algorithm classifies cases based on their similarity to other cases.

In K-Nearest Neighbors, data points that are close to each other are said to be neighbors.

K-NN paradigm

Similar cases with the same class labels are close to each other in the feature space. Thus, the distance between the two cases is a measure of their similarity or conversely, their dissimilarity.

Essentially, it comes down to calculating the distance between two data points.

For…


A comprehensive guide to starting practicing Machine Learning (ML) in Python for complete beginners with hands-on examples. Learn ML and Upgrade yourself from a complete beginner → to a ML-practitioner. Explaining the basics, motivation, and tools for Machine Learning.

Cover Photo of a girl with a robot.
Cover Photo of a girl with a robot.
Photo by Andy Kelly on Unsplash

Intro

I decided to break the ice for everyone who is just starting out on this journey of mastering the Machine Learning.

Let us be clear — Machine Learning is not Magic. Machine Learning (so-called ML) is the study of computer algorithms…


This tutorial is the starting point of my big project — “From Zero to a Machine Learning (ML) practitioner”. The main idea is to teach everybody Python and ML despite their educational background.

Cover photo to the article.
Cover photo to the article.
Photo by rishi on Unsplash

This tutorial is meant for everyone interested in Python. Especially, for those who are just starting out and cannot break the ice from intention to action. You are here which means you are serious about learning Python and I appreciate it.

I am using Python for my work a lot. Some of the applications are scientific computing, statistics, and advanced visualization. But in my free time, I enjoy creating mini-applications for various reasons. Some of them solve a particular problem (personal, or a world large-scale problem), others are just for fun, or just something to challenge myself.

This particular lesson…


Unsupervised Machine Learning in Python from scratch tutorial

Messier 13 — the Great Globular Cluster in Hercules. The best known globular clusters in the northern hemisphere.
Messier 13 — the Great Globular Cluster in Hercules. The best known globular clusters in the northern hemisphere.
Photo by Guillermo Ferla on Unsplash

After the short introduction to clustering and the practical ideas of using it, we will go through this tutorial on K-Means Clustering from scratch in Python. I will show you how it works intuitively step by step, in a way I wish somebody showed it to me. After completing this tutorial, you will learn how to:

  • generate a dataset using sklearn make_blobs function,
  • visualize the data with matplotlib,
  • understand & create your own K-Means Clustering algorithm from scratch using only numpy, a basic Python library,
  • create an animated image (.gif) using imageio library.

Introduction

Customer Segmentation

Imagine that we are a company that…


Python for time management. Pomodoro application. The full code is included :)

A laptop and a cup. The header image for my article about creating a productivity app from scratch with Python.
A laptop and a cup. The header image for my article about creating a productivity app from scratch with Python.
Photo by Artem Sapegin on Unsplash

Intro

One way to do so is to take one step at a time. Because our brain is not meant to be multitasking. In reality, it does multi-switching between different tasks.

In other words, we need to concentrate on one single activity at a time. And the Pomodoro technique can help us with it.

Summary from Part 1

Previously, we built the base…


Applying Regular Expressions (regex) to a real-world problem.

A laptop with a face mask on it.
A laptop with a face mask on it.
Photo by Guido Hofmann on Unsplash

Short Intro

What can I do for the community during this horrible pandemic? How can I help others to research the coronavirus?

I am going to apply my knowledge of Python to analyze a scientific paper on COVID-19 and to show you that everyone can use Python to analyze the text and get some insights out of it. This post is meant to encourage everyone to use Python in day-to-day life. …

Ruslan Brilenkov

Certified Data Scientist | Ph.D. candidate in Astrophysics | I write about everything I find fascinating.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store