[EXE] Predictive modeling using temporal data

[hash-ir]

Learning Goals

• Create a multi-layer perceptron model from scratch using NumPy
• Understand forward pass, backpropagation and hyperparameter tuning from the ground up

Exercise Statement

Create a 2-layer neural network using NumPy to predict future ridership data based on the historical data

Prerequisites

• Basic knowledge of NumPy and neural networks

Data source/summary:

Bike Sharing Data

(Optional) Suggest/Propose Solutions

I have the solution using NumPy that I did as part of the Deep Learning Nanodegree, will be happy to create a pull request to include the exercise statement/solution. I have written a blog post as well if someone is curious

(Optional) Further Links/Credits to Relevant Resources:

This exercise and solution's proposal came from Project 1 of Udacity's Deep Learning Nanodegree

[dermarkr]

Hi, I'd like to work on this with a couple of others for a school project. We'll be basing it on your blog post.

[hash-ir]

@dermarkr Sure, let me know if you need any help!