Skip to content

A simple neural network for parity problem using 4 bitwise inputs and outputs

License

Notifications You must be signed in to change notification settings

mertkoc/simpleNeuralNetwork

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

simpleNeuralNetwork

A simple neural network for parity problem using 4 bitwise inputs and outputs, the network is trying to identify the parity problem, that is, if there are odd number of 1 bits the output is 1 and 0 elsewhere. All activation functions are sigmoid, and matrix are used with numpy library in order to speed the calculations.

Please note that this a terrible network, and it usually gets stuck in local minimas even learning rate is very small. This could help you understand what neural networks do if you ever want to implement them yourself. Otherwise, please save yourself from the burder of wasted hours in pointless training sessions for this example.

I tried to write it as readable as possible. Hope it helps!

About

A simple neural network for parity problem using 4 bitwise inputs and outputs

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages