The aim of this GitHub is to collect useful courses, blogs, articles and videos about programming, Machine Learning (ML) and Deep Learning (DL). There are many free resources, like Deeplearning.ai that offer many free (short) courses dedicated to both general AI applications and specializations. YouTube is also a great resource for AI: Channels like 3Blue1brown offer excellent learning material about a variety of AI-related topics. While this GitHub is a great starting point, it is also advised to further explore the mentioned resources.
Good luck, and have fun learning!
Deeplearning.ai is a useful learning platform that offers a wide variety of courses related to machine, deep learning, and specializations in those fields. They offer short and long courses. You can filter by course length and difficulty. The courses themselves consist of videos and notebooks that walk you through the material. Browse through these courses and see which ones could be useful for your thesis!
Deeplearning.ai also offers a newsletter (The Batch) that keeps you up to date with recent DL advancements.
HuggingFace is an online platform that contains extensive blogs, documentation and useful Python packages for your deeplearning experiments. The HuggingFace YouTube channel posts tutorials on how to work with the platform and Python packages.
The following courses take you back to the basics of programming and some best practices.
- AI python for beginners. This course looks back on the most important aspects of the programming bootcamp: https://www.deeplearning.ai/short-courses/ai-python-for-beginners/
- Environments with Conda. Deploying environments is essential for larger Python projects. The following documentation dives into what environments are and how you can optimally set one up: https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html
- Data Analysis with Python. The following courses dive into data processing and visualization.
- Paid (7 day free trial): https://www.coursera.org/learn/data-analysis-with-python
- Free: https://www.freecodecamp.org/learn/data-analysis-with-python/
- Command Line for Beginners. This tutorial walks you through a few basic commands: https://ubuntu.com/tutorials/command-line-for-beginners#1-overview
The following article and videos offer some more theoretical insight into ML algorithms.
- Article: https://www.geeksforgeeks.org/ml-linear-algebra-operations/
- Video : https://www.freecodecamp.org/news/learn-linear-algebra-for-machine-learning/
- YouTube Playlist for more details about each algorithm: https://www.youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab&ab_channel=3Blue1Brown
The following courses and video discuss the basics of ML algorithms and how to implement them in Python.
- Course (paid): https://www.deeplearning.ai/courses/machine-learning-specialization/
- Course (free): https://developers.google.com/machine-learning/crash-course
- Video (not necessarily text-based ML): https://www.youtube.com/watch?v=i_LwzRVP7bg&ab_channel=freeCodeCamp.org
Sci-kit learn is the most commonly used Python package for implementing these algorithms. They also offer tutorials on how to do so:
The following video neatly summarizes all ML algorithms: https://www.youtube.com/watch?v=E0Hmnixke2g&ab_channel=InfiniteCodes
The following course and videos discuss how neural networks work and how they are implemented in Python.
- Course (paid): https://www.deeplearning.ai/courses/deep-learning-specialization/
- YouTube playlist: https://www.youtube.com/watch?v=aircAruvnKk&list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi&ab_channel=3Blue1Brown
- Interesting talk from Andrej Karpathy: https://www.youtube.com/watch?v=VMj-3S1tku0&ab_channel=AndrejKarpathy