I have used a Multi-Layer Perceptron (MLP) neural network to classify handwritten Persian digits dataset. I have plotted the error curve during the training phase. It has been explained what maximum accuracy is achieved. Additionally, I have examined the accuracy of recognizing different digits.

recognize mouse-written numbers using KNN, Neural Network, and Convolutional Neural Network models

A small example using WPF and ML.Net for training and recognize handwritten numbers using a stylus/pen.

Using ML to create a model which would predict/recognize the english alphabet from our own dataset.

This repository contains a notebook to take you through step by step guide on recognizing handwritten digits using a Multi-Layer-Perceptron(MLP)

Classifying handwritten digits (MNIST) using multi-layer perceptron in PyTorch.

After working on a end year project for University, showcasing the better energetic efficiency of Neuromorphic comparing two programs, I've decided to improve my second algorithm. You'll find 3 files of codes : the main programm, the calculation of its accuracy and the test on the MNIST data-base.

Capable of recognizing handwritten digits

Program in Python to solve sudoku puzzles from images, using TensorFlow (Keras) and Backtracking Algorithms.

A tutorial which helped me in order to use the model of recognizing handwritten digits with the accuracy increasing each time.

The following repository contains all the code which was used by us for our ITSP project called 'Scribble' at IIT Bombay

Neural network that reads handwritten numbers.

Recognize Handwritten Digits(persian/english) with Neural Networks

This uses the Rust-NN, compiled to WASM, to recognize digits on frontend, without sending the data to backend.

Building a deep learning model for recognizing handwritten numbers.

This program uses ML to recognize a handwritten number written anywhere on a blank paper with preferable black ink. Please make sure that the image is of apt resolution.

Super Resolution's the images by 3x using CNN

A Neural Network implemented from scratch as per http://neuralnetworksanddeeplearning.com/ in Rust. This is then trained on MNIST. This is also used in Rust-NN-Web project to compile to WASM and recognize digits.