Skip to content

itkkk/BACON

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

BACON

BinAry ClassificatiOn Network is a simple project inspired to the popular L-layer network developed as exercize during the famous Andrew Ng's course "Neural Networks and Deep Learning".
As the name says, the network can be used to perform binary classification. It exploits the RELU activation function for the first L-1 layers, while the sigmoid function is used in the latest neuron.

Implementation

I tried to make it more object oriented than the original implementation, incapsulating the forward pass, the cost computation, the backward pass and the weights update in a class called "model".

Experimentation

I tested some topology of network on two datasets, which you can find in the "datasets" folder: Catvnocat and Pima Indians Diabetes. I got 80% test accuracy for the first dataset and 71% test accuracy for the second dataset. Obviously the results are not so exciting but this is only an exercize. Tuning the hyperparameters and normalizing the data could help in achieving better performance.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors