The purpose of this project is to take handwritten digits as input, process the digits, train the neural network algorithm with the processed data, to recognize the pattern and successfully identify the test digits. The popular MNIST dataset is used for the training and testing purposes. The IDE used is MATLAB

IJCNN 2015 Hierarchical extreme learning machine for unsupervised representation learning

Graph Agglomerative Clustering Library

Numerical illustration of a novel analysis framework for consensus-based optimization (CBO) and numerical experiments demonstrating the practicability of the method

Auto-encoder Based Data Clustering Toolkit

Neural nets for high accuracy multivariable nonlinear regression.

Training an artificial neural network using back-propagation on MNIST dataset

Classify the MNIST data by LIBSVM in Matlab.

The repository implements the a simple Convolutional Neural Network (CNN) from scratch for image classification. I experimented with it on MNIST digits and COIL object dataset.

matlab for mnist dataset

This repository contains the code to reproduce all of the results in our paper: Making Learners (More) Monotone, T J Viering, A Mey, M Loog, IDA 2020.

UB Computer Vision

Hand-written digit recognition on MNIST dataset

Recognizing hand-written digits with an accuracy of 97.52%

Práticas de PDS

This repository can recognize MNIST Dataset without any tool boxes. It's a CNN demo in Matlab

Course Assignments

This repository encloses the programmatic part of the research into equivalence of Hebbian learning and the SVN formalism, exploring hypothesis brought forward in [On the equivalence of Hebbian learning and the SVM formalism [Nowotny, T and Huerta, R]