In this project, I got to build a neural network from scratch to carry out a prediction problem on a real dataset! By building a neural network from the ground up, I have a much better understanding of gradient descent, backpropagation, and other concepts that are important to know before mastering higher level toolssuch as Tensorflow. I also got to see how to apply these networks to solve real prediction problems!

The data comes from the UCI Machine Learning Database.

1. Download anaconda or miniconda based on the instructions in the Anaconda lesson.
2. Create a new conda environment:

    conda create --name dlnd python=3

3. Enter your new environment:
   1. Mac/Linux: >> source activate dlnd
   2. Windows: >> activate dlnd
4. Ensure you have numpy, matplotlib, pandas, and jupyter notebook installed by doing the following:

    conda install numpy matplotlib pandas jupyter notebook

5. Run the following to open up the notebook server:

    jupyter notebook

6. In your browser, open Your_first_neural_network.ipynb

• Udacity - Initial work - Deep Learning Repo
• Jonathan Sulivan

• Hackbright Academy
• Udacity

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Please refer to Udacity Terms of Service for further information.