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

MLP model for classifying MNIST images

NN and KNN to classify handwritten digits

This project aims to show the ideas of how to classify mnist datasets by using SVM, RF, XGBoost.

This project is about recognizing handwritten digits using custom architecture of Convolutional Neural Networks (CNN). The CNNs have been trained on a dataset of 1.5 million images, resulting in an impressive accuracy of 99.625% on Kaggle.

This project is a comprehensive solution for recognizing handwritten digits and text from images, with functionalities for training, testing, and usage, making it suitable for tasks like cheque amount verification and other handwritten text recognition applications.

KNN classifier

Contains assignments I did in ML course

Handwritten Digit Recognition with Random Forests algorithm

A Convolutional Neural Networks model used to recognize handwritten numbers.

This repository serves as a comprehensive collection of the programming assignments completed by me during the Machine Learning Specialization course. Each assignment showcases the practical application of various machine learning techniques and algorithms, underlining my growing proficiency in this domain.

ML script to train the CNN and ANN model using MNIST database to recognise numbers from the input image using Keras or Tensorflow framework

Handwritten Digit Recognition using neural nets and ML classifiers

Application which recognizes and predicts handwritten digits, drawn by user.

Build an Interface using tkinter for testing handwritten-digit-recognition

Machine learning Java implementations

A Machine Learning Project training from MNIST Dataset and recognizing handwritten digits, given as input. This is made using Python and some imported libraries like Pandas, Sklearn and Matplotlib. Also the common classifiers used to train are compared here on the basis of their accuracies.