Machine-Learning-Roadmap

Roadmap to learn AI by dBug Labs-

1. Absolute Basics of our Work

• Basic computer architecture:
  • GPU vs CPU
  • File Systems
• Linux and bash-scripting
• Containers - Docker
• Requirement files and Environments
• Git and Git-Hub

2. Data Science Stack

• Python
• NumPy
• Pandas
• Matplotlib and Seaborn
• scikit-learn
• SciPy

3. Machine Learning

• Try reading official documentation of various framework and libraries, learn to implement them the usual way and also from scratch.
• Machine Learning - Coursera (Note : this course is now divided into 3)
• MIT 6.034
• GeeksForGeeks Articles

4. Deep Learning

• TensorFlow in Practice Specialization - Coursera
• fast.ai
• Stanford University's CS224n - NLP
• DEEP LEARNING - Yann LeCun

5. Natural Language Processing

• Natural Language Processing by National Research University Higher School of Economics
• NLP course by Yandex Data School

7. Deploying/Shipping Projects

Feel free to use any of these frameworks, all are not required.

• Full Stack Deep Learning
• Full Stack Python
• TensorFlow: Data and Deployment Specialization
• Django
• Flask
• Flutter

8. Resources

Dataset Resources

• Kaggle
• Google Dataset Database

Most important stuff around AI is that it is an ever evolving field and making a perfect roadmap is not possible,so make changes as you proceed in your ML/AI/DL journey . PRs are welcome.

Open-Source Guidelines

We value keeping this site open source, but as you all know, plagiarism is bad. We spent a non-negligible amount of effort developing, designing, and trying to perfect this iteration of our website, and we are proud of it! All we ask is to not claim this effort as your own.

So, feel free to fork this repo. If you do, please just give us proper credit by linking back to our website, Thanks .