Skip to content

aniketkumar2001/MNIST-dataset-MLP-NN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MNIST-dataset-MLP-NN

Training an MLP Neural Network for MNIST Dataset using only numpy and pandas

The dataset can be downloaded in CSV format from the following link: MNIST Datasets. I implemented two neural network models: the first with two hidden layers of 16 neurons each, and the second with three hidden layers containing 56, 16, and 16 neurons. The ReLU activation function is used for the hidden layers, while the sigmoid activation function is applied to the output layer.

The two-hidden-layer model achieved an accuracy of 86%, while the three-hidden-layer model reached 96% on the test dataset, with the corresponding confusion matrix plotted for performance visualization. The weights and biases of both trained models have been saved in .npy format and are provided in zip files named WB_2HL and WB_3HL.

About

Training a MLP Neural Network for MNIST Dataset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published