An anxious and motivated beginner in AI and ML:

[NamrathaN]

Hello DeepLearning Community, I am a beginner in the field of AI and ML. While I have learnt till supervised classification and regression in ML when it comes to problem solving I am not sure how to proceed. I am in a assumption that coding would be a prerequisite and knowing ML packages like (NumPy, Pandas, Matplotlib, Scikitlearn is mandatory). I have been following Jake VanderPlas book while it is a comprehensive book which covers all the four packages but the codes in the book is outdated and I am unable to proceed. This is where I am doubting myself if this is a correct path iam heading towards. Can anyone guide me on this?

[balaji.ambresh]

Please see this:

Guide for Machine Learning, NLP, Computer Vision - (Roadmap) Feedback

Hello everyone, Hello everyone, I hope you’re all doing great! I’ve been working on an academic project for UX design, and as part of it, I had to create a new feature for any website. I thought DeepLearning.AI was a great place to apply my skills and knowledge. I started by focusing on a common problem in the community: “Where should I start? Is there any roadmap for learning AI?” This is a question I’ve seen many people post here on the forum. So, I did some research and analyzed different…

And a newer tool:

DeepLearning.AI Roadmap Generator

[g15713]

Welcome to the community — you’re asking the right questions, and many beginners feel exactly the same way when moving from “learning concepts” to actually solving problems.

Yes, basic coding + core Python libraries are essential.
You don’t need to be a software engineer, but you do need comfort with NumPy, Pandas, Matplotlib/Seaborn, and Scikit‑learn. These show up in almost every ML project.

Jake VanderPlas’ book is great, just a bit outdated.
Some APIs and plotting defaults have changed, so don’t worry if the code doesn’t run exactly as written. Cross‑check with current docs and keep going.

Feeling stuck after learning the theory is normal.
Every beginner hits this stage. What you need now is structured practice: small datasets, clear tasks, and repetition. You learn ML by building, not just reading.

A simple path forward:

• Strengthen your Python + ML tooling with modern, hands‑on courses.

• Build 5–10 small projects (house prices, digits, churn, spam, recommendations).

• Use a roadmap for direction, not perfection.

You’re not on the wrong path.
Confusion is part of the process. Keep practicing with real datasets and things will click faster than you expect.

Feel free to share what you’re stuck on — the community is here to help.

Tip: Using an AI assistant as a learning partner can really help you stay focused and avoid getting stuck. Thanks to Copilot for helping me shape this explanation.