A Java program for creating, training, testing, and managing simple neural networks on the MNIST dataset

My second neural network project. You can select the number of hidden layers and the number of neurons in the layers. Dynamic Step is experimental, thus you should keep it disabled. Overall the network is quite inefficient.

Feed-forward neural network from scratch (the only libraries I'm using are java libraries, and mostly used for reading training data) using Java. The purpose of project is to classify images as digits (numbers from 0 - 9) based on the way they look to the program using deep learning, with the help of the MNIST dataset

Hi! Thanks for checking out my tutorial where I walk you through the process of coding a convolutional neural network in java from scratch. After building a network for a university assignment, I decided to create a tutorial to (hopefully) help others do the same and improve my own understanding of neural networks.

An efficient Nearest Neighbor Classifier for the MINST dataset. It uses a VP Tree data structure for preprocessing, thus improving query time complexity

These examples use the MNIST Dataset to demonstrate and test basic flink functionality.

Repository for Digit-Recognition Application using Neural Networks and JavaFX.

Code to convert the native MNIST data format to PNG images.