Hi everyone, I wanted to share a tool I’ve been working on called Deep-0. It’s designed to generate coding challenges and exercises from any technical topic whether it’s machine learning, software engineering, financial math, or any other area you’re interested in. The idea is to turn what you’re learning into interactive, structured problems you can solve.

The tool’s still evolving, but I think it’s a neat way to bridge the gap between reading and actually working through the ideas. If you’re curious to see how it works or have suggestions, here’s the link: https://deep-ml.com/deep0

Would love to hear if you’ve tried similar approaches or have ideas for where this could go next!

Hi,

We've introduced some new features to Deep-ML designed specifically to help you master challenging topics more effectively.

One of these features is problem breakdown. With this capability, you can approach any complex machine learning problem by breaking it down into smaller, more manageable pieces. This approach makes it easier to pinpoint exactly where you're getting stuck, helping you to learn faster and solve problems more confidently. This feature is accessible to everyone on the daily question and available for all other questions with the premium subscription.

We've also added collections—a way to test your understanding of key concepts thoroughly. Collections help you determine if you truly grasp a topic by guiding you through carefully structured problems based on influential resources like the "Attention Is All You Need" paper or Andrej Karpathy's Micrograd tutorial. Completing these collections earns you badges, providing clear evidence of your knowledge and abilities—without needing a formal degree.

We'd love to hear your thoughts!

The backbone behind https://www.deep-ml.com

I have been working on a platform where people could solve ML problems similar to leetcode but more focused on learning and less on interview https://www.deep-ml.com/, also started making the problems open source https://github.com/Open-Deep-ML/DML-OpenProblem

I've created a website https://www.deep-ml.com/ where learners can practice and implement machine learning algorithms using only numpy. Now, I'm making all the problems open source on GitHub: https://github.com/Open-Deep-ML/DML-OpenProblem.

The goal is to provide a resource where people can dive deep into the fundamentals of machine learning without relying on high-level libraries, making the learning process more transparent and hands-on. Contributions and feedback are welcome!

Thank you for the help! Will definitely try this instead of my current method, if you’d like you could join the discord https://discord.gg/s4uVTQwk and let me know if you have any other ideas

Thank you for the feedback will look into that

Edit: the sign up works for me, but the spacing is an issue

Originally I started this as an open source project, and currently thinking of a similar system to what you shared where I make the problems open source and keep the site close sourced. Here was my original project https://github.com/moe18/DeepMLeet

That is a good point, thank you for the input I will change up the example problem to clear things up

Created a discord for anyone that had any recommendations or wants to stay up to date on new questions we are working on https://discord.gg/s4uVTQwk