Skip to content

This is implementation of a neural network using Julia for classification of MNIST dataset. It doesn't use any machine learning libraries. Primary purpose for this project is to learn neural networks basics and Julia language. Julia language is relatively new amongst other preferred language for data science.

Notifications You must be signed in to change notification settings

eelectronn/neuralNets-Julia

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Network Implementation in Julia

This is implementation of a neural network using Julia for classification of MNIST dataset. It doesn't use any machine learning libraries. Primary purpose for this project is to learn neural networks basics and Julia language. Julia language is relatively new amongst other preferred language for data science.

About the dataset

MNIST is dataset of labelled 28 x 28 images of handwritten digits. There is training set with 60,000 images and a testing set of 10,000 images. All images in both the sets are labelled. The primary goal is to classify these images by identifying the digit it represents. More information about the dataset and its source is available here.

Examples from dataset

Following examples are produced with Plots and Images package available for Julia.

Acknowledgements

Thanks to Michael Nielsen for crafting a wonderful book on neural networks and deep learning. It's is great source for someone to start out with neural networks. It covers all the basics about neural nets and more importantly the math that make them work. This book has been followed in a great capacity for this project.

About

This is implementation of a neural network using Julia for classification of MNIST dataset. It doesn't use any machine learning libraries. Primary purpose for this project is to learn neural networks basics and Julia language. Julia language is relatively new amongst other preferred language for data science.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages