Deep Learning using the platform H2O and R

Recognizes handwritten digits using Keras and convnets

Implementation of a Convolutional Neural Network for Handwritten Digit Recognition

Tensorflow implementation of Conditional GAN trained on MNIST dataset

Machine Learning and Neural Network techniques to recognize handwritten digits with high accuracy

Get and solve the handwriting dataset from MNIST

Interactive Handwritten Digit Recognition: An intuitive Keras and TensorFlow powered app with Streamlit UI. Draw and predict digits in real-time.

Handwritten Digit Recognition is the capacity of a computer to interpret the manually written digits from various sources like messages, bank cheques, papers, pictures etc

Handwritten digits, a bit like the MNIST dataset.

Simple application for digit recognition with CNN using four different datasets

Figuring out which handwritten digits are most differentiated with PCA.

Achieved an accuracy of 90% in Handwritten Digit Recognition by implementing K-Nearest Neighbor(K-NN) algorithm on MNIST dataset (a database of several handwritten digits ) to recognize any handwritten digit.

Recognition of handwritten digits using neural networks (From scratch)

This is an example for how handwritten digits can be learnt with random forests

Deep Neural Network for MNIST Classification

Learns using the input from the testing_data how to compute the output

A simple web app using a neural network to classify digits drawn by the user

A simple implementation of a Restricted Boltzmann Machine, able to perfrom a supervised classification task on the MNIST database of handwritten digits, coded for prof. Bortolozzi course Biological Physics @unipd

Create a model based on the `MINIST` dataset of Handwritten Digits.

Trained a Convolutional Neural Network (CNN) to predict the handwritten digits from MNIST dataset and visualized the results in the form of an interactive Webapp using streamlit.