Math for neural networks
Neural networks are more complex models and they are also pretty exciting. When I started to learn Data Science I jumped right into implementing one with no idea how they worked and what I was doing. All I knew was that my code ran and the results were not so promising. I found myself getting a bit frustrated and decided to take a step back and do the work (that is learn the theory with the help of my Thesis supervisor). This week I will provide links to materials that can help you understand how neural networks work starting with the content produced by me.
My success story
After learning all these basics I developed a solution to predict acts of violence and protest in South Africa with a high degree of accuracy using neural networks. Have a read through here:
Referenced Learning Material
- Grokking Deep Learning: this is an ebook with the first couple of chapters free
- Computational Linear Algebra for Coders : Look at Matrix and Tensor Products and Matrix Decompositions section
- 3Blue1Brown : Animated math
- How to Learn Deep Learning (when you’re not a computer science PhD) : Get inspired