Practical Deep Learning from is Back!

Looking for a great course to go from machine learning zero to hero quickly? has released the latest version of Practical Deep Learning For Coders. And it won't cost you a thing.

Practical Deep Learning from is Back!

Despite having never left, is back with the latest version of their (free!) flagship course, Practical Deep Learning for Coders.

If you have been around the machine learning space for any length of time, you are undoubtedly already familiar with, their courses, their book, their software, their founders, or some subset of these. But just in case you aren't, what is Practical Deep Learning for Coders?


A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.


Previous iterations of the course have been taken by hundred of thousands of students form around the world. This latest iteration is a completely-rewritten version of the course, which has been in the works for two years. If that's the case, you would think that there must be a lot of updates and differences from the previous implementations... and there are! Here are a few highlights:

  • A much bigger focus on interactive explorations. Students in the course build simple GUIs for building decision trees, linear classifiers, and non-linear models by hand, using that experience to develop a deep intuitive understanding of how foundational algorithms work
  • A broader mix of libraries and services are used, including the Hugging Face ecosystem (Transformers, Datasets, Spaces, and the Model Hub), Scikit Learn, and Gradio
  • Coverage of new architectures, such as ConvNeXt, Visual Transformers (ViT), and DeBERTa v3


This is a mix of foundational and state of the art stuff, folks.

The course is put together by famed machine learning researcher, practitioner, and entrepreneur Jeremy Howard, for the company co-founded by he and the equally celebrated Rachel Thomas. These aren't newcomers to the scene trying to cobble together a course on something they just learned; this is the culmination of years of understanding, distilled into nine 90 minute lessons. Oh, and did I mentioned that it's free?

What are you going to learn in this course?

  • Build and train deep learning models for computer vision, natural language processing, tabular analysis, and collaborative filtering problems
  • Create random forests and regression models
  • Deploy models
  • Use PyTorch, the world’s fastest growing deep learning software, plus popular libraries like fastai and Hugging Face


Again, this ranges from the basics of machine learning (regression models) to some of the most recent and currently relevant libraries (PyTorch, Hugging Face, and fastai) to the beyond (deploying models).

And what will you know after taking the course? A few things specifically mentioned on the course site include: how to train state of the art computer vision, NLP, tabular, and collaborative filtering models; how to deploy your trained models as web apps; an in-depth understanding of deep learning (pun intended), which can be used to build and improve your own models; practical techniques that actually matter.

Don't let the opportunity to learn practical, relevant machine learning from an expert — in every sense of the word — pass you by. The course is brand new, as up to date as is possible, and covers topics that will help you excel in implementing your own machine learning and deep learning models.

Also, did I mention that it's free?!?

Head over to the Practical Deep Learning for Coders website and get started now!

Matthew Mayo (@mattmayo13) is a Data Scientist and the Editor-in-Chief of KDnuggets, the seminal online Data Science and Machine Learning resource. His interests lie in natural language processing, algorithm design and optimization, unsupervised learning, neural networks, and automated approaches to machine learning. Matthew holds a Master's degree in computer science and a graduate diploma in data mining. He can be reached at editor1 at kdnuggets[dot]com.