Following are a few resources to help understand Artifical Neural Nets / Deep Learning.

- [Brilliant intro to ANN](https://brilliant.org/wiki/artificial-neural-network/). Noteworthy: **Universal Approximation Theorem**
- [Brilliant intro to Backpropagation](https://brilliant.org/wiki/backpropagation/)
- [Russel and Norvig's Artificial Intelligence, A Modern Approach, 4th Global Edition](https://dl.ebooksworld.ir/books/Artificial.Intelligence.A.Modern.Approach.4th.Edition.Peter.Norvig.%20Stuart.Russell.Pearson.9780134610993.EBooksWorld.ir.pdf)
- [Lectures by Florian Marquardt: Machine learning for physicists](https://machine-learning-for-physicists.org/)
- [CS231n.stanford.edu](https://cs231n.github.io/)
- [Layer and Batch normalization](https://www.pinecone.io/learn/batch-layer-normalization/)
- [Batch vs Online learning](https://visualstudiomagazine.com/Articles/2014/08/01/Batch-Training.aspx)
- Types of learning
  - [Zero-Shot](https://www.ibm.com/topics/zero-shot-learning)
  - [Self-supervised](https://www.ibm.com/topics/self-supervised-learning)
- Reflections on scaling
  - [Prediction: Human-equivalent neural networks by 2030](https://daveshap.github.io/DavidShapiroBlog/singularity/2021/02/19/human-scale-dnn-2030.html)
  - [The Scale of the Brain vs Machine Learning](https://www.beren.io/2022-08-06-The-scale-of-the-brain-vs-machine-learning/)
- [End-to-end learning, the (almost) every purpose ML method](https://towardsdatascience.com/e2e-the-every-purpose-ml-method-5d4f20dafee4)