Project for the Udacity Nanodegree program: Deep Learning. A first neural network for predicting daily bike rental ridership.
In this project and in the framework of the aformentioned Udacity nanodegree program, I build a neural network to carry out a prediction about daily bike rental ridership on a real dataset! I apply forwardpass gradient descent, backpropagation and other related concepts directly with python code (and without using any other higher-level tool such as PyTorch).
The data comes from the UCI Machine Learning Database: https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset
The network is trained and used by means of a Jupyter Notebook written in python: "Predicting_bike_sharing_data.ipynb"
The neural network itself is built in the pytho file: "my_answers.py"
Just clone the repository in your working directory, open the Jupyter Notebook and run it.