Deep learning applications with different datasets.

we aim to provide a framework for understanding the linguistic and cultural diversity of the Arabic-speaking world and to help scholars and researchers analyze and compare these dialects. So we developed a model that takes a text as an input and gives you the name of the dialect as an output.

Partial port of capmangrad to the Rust programming language

Image classification using FC and CNN networks on CIFAR-10.

Easy to use library to create Neural Networks in C++

Classification of different landcover classes using Hyperspectral data.

Classification of wine quality based on its parameters using fully connected artificial neural network

Train a Tic-Tac-Toe and a Connect-4 player using the TD-lambda algorithm

Model Optimization

Sentimental analysis on IMDB using tflearn Deep Neural Network

Digit recognition fully-connected neural network using the MNIST dataset, with support for batch and stochastic descent.

This repository contains my project for computer vision.

Simple Python implementation of a fully connected neural network

Python illustration of Neural net from scratch

Yet another basic neural network implementation heavily inspired by, and based on, micrograd

Fundamentals of Artificial Intelligence and Deep Learning Frameworks

This project aims to classify blood cell images from the BloodMNIST dataset using various machine learning models. Implemented classifiers include Logistic Regression, Fully Connected Neural Networks, Convolutional Neural Networks, and MobileNet. The dataset is pre-processed, and models are trained and evaluated to determine their effectiveness.

A project for my Advanced Artificial Intelligence class to apply AI methods to a real-world problem.

Fully connected deep net written in Java