This series of post will list some good articles about how to implement a neural network. Thanks for the authors for the excellent work. 
If you are the author and you don’t want your articles listed here. Please email to learn4master, we will remove it from the site. 
 

How to implement a neural network Part 1

 From: http://peterroelants.github.io/posts/neural_network_implementation_part01/

This page is part of a 5 (+2) parts tutorial on how to implement a simple neural network model. You can find the links to the rest of the tutorial here:

• Part 1: Linear regression
• Intermezzo 1: Logistic classification function
• Part 2: Logistic regression (classification)
• Part 3: Hidden layer
• Intermezzo 2: Softmax classification function
• Part 4: Vectorization
• Part 5: Generalization of multiple layers

The tutorials are generated from Python 2 IPython Notebook files,

Vectorization

This part will cover:

• Vectorization of backpropagation
• Gradient checking
• Momentum

The previous tutorial described a very simple neural network with only one input, one hidden neuron and one output. This tutorial will describe a neural network that takes 2-dimensional input samples, projects them onto a 3-dimensional hidden layer, and classifies them with a 2-dimensional softmax output classfier, this softmax function is explained in intermezzo 2 . While we didn’t add the bias parameters to the previous 2 models, we will add them to this model.