Quantum MNIST using amplitude encoding instead of dimensionality reduction.

An autonomous navigation system for drones in both urban and rural environments.

I implemented a Naive Bayes classifier form scratch and applied it on MNIST dataset.

An MNIST dataset classifier implemented from scratch in NumPy.

MNIST handwritten digit classification using PyTorch

This repo hold CV models for the Classification of single digit images. I used Pytorch and the Digit-Recognizer kaggle dataset for the training.

Test project for neural networks - Handwritten digit recognition on MNIST dataset

Problems Identification: This project involves the implementation of efficient and effective KNN classifiers on MNIST data set. The MNIST data comprises of digital images of several digits ranging from 0 to 9. Each image is 28 x 28 pixels. Thus, the data set has 10 levels of classes.

A bare-bones (minimal dependencies) implementation of some ML algorithms (classifying/clustering) as part of the Machine Learning postgraduate course assignments in the GUC

Machine Learning model that recognizes hand written digits

OCR for numbers in the MNIST dataset using various ML techniques.

All my machine learning projects and tests.

MNIST Classification with Convolutional Neural Networks

Artificial neural networks processed with Tensorflow

MNIST classifier using CNTK written in C++ and C#. Only used fully connected layers.

No description provided.

This project implements a CNN for handwritten digit classification on the MNIST dataset using PyTorch. It uses stacked convolutional layers with dropout, batch normalization, and max pooling to classify 28×28 grayscale digits (0–9) with Softmax output.

No description provided.

Digit Recognizer - Convolutional Neural Network trained with mnist model using matplotlib - Duke University Class

Performs OCR on the MNIST dataset. From my BSc. AI & Robotics at Prifysgol Aberystwyth

Naive Implementation of PyTorch framework to solve the MNIST-Digit_Recognition Problem

No description provided.

No description provided.

No description provided.

Handwritten Digit Recognition by MNIST

Deep learning demos using MNIST data set with multiple neural network models

"Quantum-Inspired MNIST" achieved 72% accuracy using nothing but means, addition, and subtraction. This experiment adds standard deviations.

Inspired by quantum classification, this is MNIST with no models, no weights, no activation functions, no optimizers, nor anything else that resembles traditional MNIST implementations.

A CNN for MNIST Dataset in Python

Feed forward neural network using Numpy for MNIST classification.