Skip to content

mcqueg/numpy_net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 

Repository files navigation

view notebook here

The motivation behind building numpynet is to obtain a deeper understanding of neural network intuition and the math behind forward and backward propagation.

ANN_URL

Training Results

training

Model Accuracy on Test Set: 92.18%

CNN accuracy

  • training: 99.52%
  • testing: 98.55%

About

a simple neural network using pure numpy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published