This project implements a deep learning model to recognize handwritten digits (0-9) using the MNIST dataset.

A resource-conscious neural network implementation for MCUs

Handwritten digit recognition using the MNIST dataset. Features a Streamlit GUI where users can draw digits, which are then evaluated by a PyTorch neural network model for prediction.

This repository focuses on handwritten digit recognition using the MNIST dataset. It includes implementations of Logistic Regression, MLP, and LeNet-5 in PyTorch, organized into folders for reports, flowcharts, scripts, and notebooks, with detailed instructions for preprocessing and training.

Handwritten Digit Recognition using Python

Experiments on MNIST dataset and federated training using Flower framework

In this notebook, my objective is to explore the popular MNIST dataset and build an SVM model to classify handwritten digits. Here is a detailed description of the dataset.

A hello-world of deep learning - neural net to classify handwritten digits.

No tf, no pytorch, just math using MNIST dataset

🚀 Mnist learning with Tensorflow and Serving with FastAPI

This project uses autoencoders to denoise MNIST images, aiming to improve handwritten digit recognition by refining classifier training data

Handwritten digits image classification with the MNIST dataset using MultiLayer Perceptron.

Quantum GAN Model to generate images with limited qubits

Simple Neural Network written from scratch in C++ with a real time interactive and visualization demo.

I used the MNIST dataset for the implementation of a handwritten digit recognition app. To implement this, will be using a special type of deep neural network called Convolutional Neural Networks. In the end, I also build a Graphical user interface(GUI) where you can directly draw the digit and recognize it straight away.

Exploring the depths of generative learning with a $\beta$-Variational Autoencoder ($\beta$-VAE) applied to the MNIST dataset for robust digit reconstruction and latent space analysis.

Thoughts about Artificial Intelligence using the toy dataset MNIST

A zip file containing images for MNIST-M dataset

Hybrid neural network model is protected against adversarial attacks using either adversarial training or randomization defense techniques

This project implements a handwritten digits classifier using PyTorch. The goal is to accurately classify these images into their respective digit classes.