Skip to content

jmribeiro/NumPy-Neural-Network-From-Scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NumPy Neural Network From Scratch

Neural network implemented using nothing but NumPy (no autograd), showcased for multi-class classification, with OCR dataset.

All parameters optimized using the Stochastic Gradient Descent algorithm.

Running:
$ pip install numpy matplotlib
$ python train.py
Default Hyperparameters:
-epochs 20 
-num_layers 2 
-hidden_size 64 
-activation relu
-learning_rate 0.1
-l2_penalty 0.0
-batch_size 32

Output

About

Neural network implemented using nothing but NumPy (no autograd), showcased for multi-class classification, with OCR dataset.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages