Lessons in the fundamentals of artificial neural networks
This repository contains a collection of articles and smaller projects aimed at improving the understanding of artificial neural networks. Those articles are primary focused on teaching. Some of the methods are unconventional and not suited for use in production. My aim is to peel back some of the outer layers of neural networks and look beneath them. This is great for learning, but I recommend using the abstraction established frameworks provide when writing production quality code.
So please use these resources as they were intended to - as a source of information and guidance to sharpen your understanding of neural networks. The best way to learn is to experiment and try out new ideas. I provide all the code I wrote in this repository as well, so feel free to use and modify it as you see fit. Keep on learning and enjoy the process!
Table of Content
- Regression Analysis - Part 1: Simple Linear Regression
- Regression Analysis - Part 2: Multi-Dimensional Linear Regression
- Regression Analysis - Part 3: Polynomial Regression
- Regression Analysis - Part 4: Regression Metrics
- Regression Analysis - Part 5: Measuring the Quality of Polynomial Models
- Regression Analysis - Part 6: Gradient Descent
- more to come...