Coding Machine Learning Algorithms

Name: Coding Machine Learning Algorithms
Rating: 4.7 (67 reviews)

4.782 hours4K learnersCertificate

ML libraries make model building simple, but deep understanding is crucial for reliable results. Implement the main ML algorithms in Python to better understand how they work. This course is not about using pre-coded ml algorithms. Instead, you will code those on your own.

Provided by

JetBrains Academy

See course content4 weeks ago last updated

No credit card required

Our students are building their future at:

Study at your own pace

Fit learning around your schedule. Suitable for all levels.

Learn from the experts

Short, practical text lessons by seasoned developers.

Become job-ready

Integrated with professional tools by JetBrains.

Join the community

Trusted by learners worldwide, confirmed by Trustpilot

What you'll learn

After completing this course, you will be familiar with the theory behind the most commonly used machine learning algorithms. You will get the experience of implementing these algorithms from scratch. You will also build a strong foundation for implementing and customizing more complex, state-of-the-art models, which is something ML engineers regularly do.

More precisely, you will:

Get to know the basic algorithmic concepts behind ML models;
Familiarize yourself with math fundamentals for machine learning: matrix algebra, derivatives, and probability theory;
Use your theoretical knowledge to create fully working algorithms in Python;
Get hands-on experience with a basic data science workflow.

See course content

Learn by doing

# 1

Apply knowledge into practice

You already know the theory. Now it's time to code like you do at work—in a professional IDE, with real project constraints, solving problems that actually matter. Welcome to software engineering as it should be.

# 2

Navigate complexity with surgical precision

Most developers waste months learning random concepts without seeing how they connect. Our interactive Knowledge Map fixes this. It shows exactly how every programming concept relates to others, helping you build a structured mental model of coding.

# 3

Copy the best. Then improve.

Here's what top engineers do that others don't: they study other people's code obsessively. When you get stuck on Hyperskill, you can explore solutions published by other developers. See their exact code. Understand their approach. Learn their tricks.

# 4

Code review that actually makes you better

We stripped code review down to what actually matters: does your solution work? Have you handled the edge cases? Is there a cleaner way to write this? Hyperskill acts like a competent reviewer who actually tests your code. Not genius-level analysis, not architecture debates — just solid feedback on making your code better.

Elevate your engineering mastery through real-world challenges

Master advanced engineering concepts through ambitious projects. Each project deepens your expertise and transforms you from an experienced engineer into an exceptional one.

Decision Tree from Scratch

A decision tree is one of the most widely used machine learning algorithms due to its ease of interpretation. This algorithm is similar to the way we make decisions in our daily life.
In this project, you will take a closer look at the algorithm and write it from scratch with the help of Python, NumPy, and Pandas. Teach the model to process categorical and numerical features to make data-based decisions. Implement a decision tree for classification and apply it to a real dataset.

Graduate

Linear Regression from Scratch

Linear relationship estimation is probably the first kind of modeling we come across at school. Linear regression is one of the most popular methods for estimating linear relationships and one of the most popular machine learning algorithms. This project explains how the linear regression algorithm works. These basics will help you with model interpretation and debugging if you want to fit and predict linear models.

Graduate

Neural Network from Scratch

Let's train a very simple but fully connected neural network! In this project, we'll create the necessary metric functions and use custom feedforward and backpropagation methods and functions, all done by hand. The dataset for this project is Fashion-MNIST – no more boring number recognition.

Graduate

Explore all projects

Topics covered by this course

Math

66 topics

Programming languages

63 topics

Data science

47 topics

Fundamentals

8 topics

System administration and DevOps

2 topics

Algorithms and Data Structures

1 topic

Learn from the industry experts

JetBrains Academy

JetBrains Academy is a part of JetBrains, a global software company specializing in the creation of intelligent, productivity-enhancing tools for software developers and teams. With years of expertise in software development and education, JetBrains Academy empowers more than a million people worldwide to learn and teach computer science, and help organizations inspire their teams to reach their goals in tech. Professional development tools play a big role in computer science education. This is why JetBrains Academy courses offer integration with JetBrains IDEs. This integration assists learners in getting experience with real development processes to streamline their learning curve at future work.

Your peers think Hyperskill rocks

Roland Onderka

7 months ago

Really great, to understand the basics from (non) linear multiple regression up to neural networks

alcala21

3 years ago

I've learned about Machine Learning algorithms and how to implement them in Python.

Viktor Reshetnikov

3 years ago

Some math, intermediate concepts of ML. It was very informative and mainly well organized and intelligibly written. Additionally want to thank the task creators for the downloadable datasets.