SathwikTejaswi / Neural-Networks-From-Scratch Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

This repository contains the implementation (from scratch in python) of a simple neural network to classify MNIST. It can also be used to classify other image datasets.

0 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
MNISTdata.hdf5		MNISTdata.hdf5
Model_output_1.png		Model_output_1.png
NN.py		NN.py
README.md		README.md
model_output_2.png		model_output_2.png
utils.py		utils.py

Repository files navigation

Neural-Networks-From-Scratch

Classification of a MNIST dataset using a single hidden layer neural network (python)

The implementation depends on the following libraries : numpy, pandas, h5py

A sample output from the model is shown below. (Note : test accuracy (97%) is displayed as 0.97)

About

This repository contains the implementation (from scratch in python) of a simple neural network to classify MNIST. It can also be used to classify other image datasets.

python machine-learning deep-neural-networks neural-network numpy python3 mnist neural-networks classification mnist-handwriting-recognition scratch-implementation

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%