A lot of machine learning courses relay on frameworks that abstract the inner workings of what's going on. If you want to become proficient, it's helpful to understand how things work under the hood.

We just published a course on the freeCodeCamp.org YouTube channel that will teach you how to use machine learning and neural networks without any frameworks.

Dr. Radu Mariescu-Istodor created this course. He has a PhD in computer science and is creates engaging and creative software tutorials.

In a world where machine learning is becoming increasingly prevalent, understanding the underlying concepts and algorithms has never been more crucial. The course doesn't rely on pre-existing libraries. Instead, it takes you through building a machine learning system from scratch.

The course centers around a captivating project: creating a web app that learns to recognize drawings. This is Phase 2 of the course, where the focus shifts towards enhancing the accuracy of the methods developed in Phase 1 (but you can still follow along if you did not watch Phase 1).

Through a series of comprehensive sections, you'll explore advanced features, classification methods, data cleaning techniques, and a wide array of fundamental concepts that are essential to machine learning.

The course is structured to gradually build your understanding from the ground up. Here are the topic sections of this course:

  • Introduction
  • Phase 1 Code Review
  • Data Cleaning
  • Confusion Matrix
  • Euclidean Distance Marker
  • Measuring the Elongation
  • Measuring the Roundness
  • Vector vs Raster (Pixels)
  • Neural Networks
  • Optimizing Neural Networks
  • Deep Neural Networks

By unveiling the inner workings of machine learning systems, you'll not only develop a profound understanding of the subject but also hone your software development skills.

Watch the full course on the freeCodeCamp.org YouTube channel (4-hour watch).