Neural network tutorial - [Part 1] - First working example in python
In this video we put code on paper!
We will be using data from the US Climate Reference Network (ftp://ftp.ncdc.noaa.gov/pub/data/uscrn/products/daily01/2017/) to fit a simple line through daily temperature and humidity measurements using the simplest neural network technique described in the last video. All of which will be done in around 20 lines of python code.
Goal:
Try to predict relative humidity using temperature by fitting a line all through the magical guesswork of neural networks
Things we will do:
1) load data from csv using pandas
2) see what our data and the slope look like using seaborn
3) initialize the unknown variables (slope and intercept)
4) take a guess at y and update the slope and intercept guesses
5) see a pretty animation of the line converging towards the answer over time
Note: Neural networks are not the best method for fitting a line there is a much more direct way for doing this which is exactly what most math libraries use. This is just to build up understand of neural networks.