# Beginner’s resources for AI

## Beginner Friendly Resources


If you're new to the field and have no prior experience, you can start with these resources in the suggested order to build your understanding of machine and deep learning.

- **A Basic Introduction to Deep Learning:**[Neural Networks by 3Blue1Brown](https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi)
- **Basic Python:** [CS50 2023 - Lecture 6 -Python](https://www.youtube.com/live/5Jppcxc1Qzc?feature=shared)
- **An Introductory Course in Deep Learning:** [Deep Learning Specialization](https://www.coursera.org/specializations/deep-learning) (Apply for financial aid beforehand, simply fill the info, everyone gets it.)
- **Reference Book:** [The Deep Learning Book by Michael Nielson](http://neuralnetworksanddeeplearning.com/)

## Further Resources

Now that you've gone through the initial resources and gained some basic experience with machine and deep learning, you can dive deeper into the mathematical and theoretical aspects. The resources below will help you better understand the math behind these algorithms and equip you with the skills necessary to take on hands-on projects.

For a detailed list of advanced deep learning resources check out our [DL Topics](https://github.com/vlgiitr/DL_Topics) repository.

### Maths for AI

- **An Introduction to Linear Algebra:** [Linear Algebra 3Blue1Brown](https://www.youtube.com/playlist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)
- **An intuition behind how derivatives are calculated using Python:** [Automatic Differentiation](https://www.youtube.com/watch?v=wG_nF1awSSY&ab_channel=AriSeff)
- **A Review of Probability and Linear Algebra Required for AI:** [Linear Algebra Review Notes](https://cs229.stanford.edu/summer2019/cs229-linalg.pdf) , [Probability Review Notes](https://cs229.stanford.edu/section/cs229-prob.pdf)

### Machine Learning


- **An Intro To Machine Learning (Essential):** [StatQuest ML Playlist(For visual intuitions)](https://youtube.com/playlist?list=PLblh5JKOoLUICTaGLRoHQDuF_7q2GfuJF&feature=shared)
- **An Advanced Course of Machine Learning (Optional):** [Stanford CS229:Andrew NG](https://www.youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU)

## Deep Learning

Now that you've completred the basics of machine learning and advanced math, it's time to explore more advanced deep learning topics. Start by learning PyTorch, and then dive into either Computer Vision or NLP, whichever excites you more.
A reference book that you can follow , [Ian Goodfellows Deep Learning Book](https://www.deeplearningbook.org/)

### Pytorch

- **An introduction to Pytorch by Andrej Karapathy:** [Neural Networks: Zero to Hero](https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ)
- If you like to follow video tutorials , you can follow [Pytorch Tutorials](https://www.youtube.com/playlist?list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz) or otherwise if you like to read you can simply refer to the [Pytorch Documentation](https://pytorch.org/tutorials/index.html)
- **Huggingface NLP Tutorials:** [Huggingface NLP Course](https://huggingface.co/learn/nlp-course/chapter1/1)

### Computer Vision

- **An Introductory Course by University of Michigan**: [Deep Learning for Computer Vision: Michigan Online ](https://youtube.com/playlist?list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r&feature=shared)

### NLP

- **An Introductory Course by Stanford University:** [Stanford CS 224n](https://youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4&feature=shared)

### A Practical Deep Learning Course

- **Practical Deep Learning by fast.ai(Optional):** [Practical Deep Learning Course](https://course.fast.ai/)

## Advanced AI Topics

Once you're familiar with the topics above, you can choose to explore some specialized areas. These are **optional** and focus on very specific sub-domains within AI.

### Reinforcement Learning

- **RL Course by UC Berkley:** [UC Berkley CS 285](https://www.youtube.com/playlist?list=PL_iWQOsE6TfVYGEGiAOMaOzzv41Jfm_Ps)
- **Deep RL Course by Huggingface:**[Huggingface Deep RL Course](https://huggingface.co/learn/deep-rl-course/unit0/introduction?fw=pt)
- **OpenAI DeepRL Course:**[OpenAI DeepRL Course](https://spinningup.openai.com/en/latest/)

### AI Security

- **AI Security Blogs:** [Cleverhans Blogs](https://www.cleverhans.io/)
- **Simons Institute AI Security Talks:**[Large Language Models and Transformers](https://www.youtube.com/playlist?list=PLgKuh-lKre12qVTl88k2n2N37tT-BpmHT)

### Meta Learning

- **Meta Learning Course by Stanford:**[Deep Multi-task and Meta Learning Stanford CS 330](https://www.youtube.com/playlist?list=PLoROMvodv4rOxuwpC_raecBCd5Jf54lEa)