Skip to content
Repository for Digit-Recognition Application using Neural Networks and JavaFX.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
src/main
target
README.md
mnist-model.zip
nb-configuration.xml
nbactions.xml
pom.xml

README.md

Digit-Recognition-App

Handwritten Digit Recognition Application uses Deeplearning4j and Neural Networks to classify digits.

Deeplearning4j

https://deeplearning4j.org/

Deeplearning4j is an Open-Source, Distributed, Deep Learning Library for the Java Virtual Machine.

MNIST Dataset

http://yann.lecun.com/exdb/mnist/

The Dataset used is MNIST Dataset. It is a subset of a larger set available from NIST. The digits have been size-normalized and centered in a fixed-size image. The MNIST problem is a dataset developed by Yann LeCun, Corinna Cortes and Christopher Burges for evaluating machine learning models on the handwritten digit classification problem. Each image is a 28 by 28 pixel square (784 pixels total). A standard spit of the dataset is used to evaluate and compare model, where 60,000 images are used to train a model and a separate set of 10,000 images are used to test it.

Screenshots

The Screenshots of the Application are attached: screenshot_1 screenshot_2 screenshot_3 screenshot_4 screenshot_5

You can’t perform that action at this time.