Benlala Raid Athmane

Arabic-Sign-Language-Image-Classification-With-CNN. This project aims to build a robust image classification model to recognize and classify Arabic sign language gestures. Using deep learning techniques and convolutional neural networks (CNNs), the goal is to facilitate communication for the deaf and hard of hearing communities by translating sign language gestures into written Arabic text.

MyPortfolio. This portfolio showcases my expertise in UI/UX design and AI projects. It highlights my work in machine learning, computer vision, and NLP, along with interactive designs and responsive web interfaces. Built using modern frameworks to ensure optimal performance and user experience.

AgraNova-AI-Agriculture. AgraNova – AI-powered notebooks for smarter agriculture in Algeria: Crop recommendation, plant disease detection, and drought prediction using machine learning and satellite data.

NEU-Surface-Defect-Classification. A web application for analyzing and classifying surface defects in steel using the NEU Surface Defect dataset and a pre-trained PyTorch model.

SmartTube. Smart YouTube Downloader & AI Assistant A modern web app built with FastAPI and LangChain that lets you download YouTube videos and chat with their content using RAG technology. Features real-time download progress, subtitle analysis, and a clean Material Design UI.

UNET-from-scratch. This project implements a U-Net architecture for car image segmentation using the Carvana dataset. The model is built with PyTorch.

FlickrCaptionator. A modern, immersive web application featuring a sleek dark-themed UI that leverages deep learning for accurate image captioning. It integrates a powerful model combining VGG16 for feature extraction and LSTM for text generation, trained on the Flickr dataset to deliver meaningful and context-aware captions.

AI-Style-Transfer-Web-App. This web application allows users to apply artistic styles from one image to another using neural style transfer techniques. The application combines a FastAPI backend with a Next.js frontend to provide a seamless user experience.

RL-for-Ramp-Metering-Highways. This repository details the use of Reinforcement Learning (RL), specifically Q-Learning and Deep Q-Networks (DQN), to create an adaptive ramp metering system for highway traffic management.

where-s-wally-object-detection. You are required to **create and train a custom object detection model** to solve a simplified object detection task. Additionally, you will implement the same task using a **pre-trained YOLO model**.

covid-19-prediction-model. application des modèles de Random Forest, Decision Tree, XGBoost, Logistic Regression, KNN et SVM sur les données prétraitées, en optimisant chaque algorithme pour maximiser le rappel de la prédiction de la COVID-19.

landscape-CNN. Jupyter Notebook

MNIST-Digit-Recognizer-CNN-Visualization-Web-App. This web application allows you to visualize how a CNN (Convolutional Neural Network) processes MNIST digit images. You can upload an image of a handwritten digit, and the app will show you the feature maps at each layer of the CNN and provide the final prediction.

AgraNovaWebApp. A Next.js mobile application for the AgraNova project, part of the Algerian AI Olympiades. This application provides smart agriculture solutions to help farmers make data-driven decisions.

New-Portfolio. A modern, responsive portfolio website designed for machine learning professionals. This portfolio showcases skills, projects, experience, and education in the field of machine learning and UI/UX design.

recommendation-system-tic-tac-toe. A web application that contain two sections, an expert system that suggest for you best PC Software & programs and Tic Tac Toe game using MinMax search Algorithm

Deep-Learning-For-Hadeeth-Recognition. This project implements an Arabic character recognition system specifically designed for Hadeeth texts (Islamic narrations) using deep learning techniques. The system segments Arabic text images into individual characters and uses a Convolutional Neural Network (CNN) to recognize and classify each character.

Pulmonary-Nodule-Detection. This web application allows users to upload chest X-ray images and detect pulmonary nodules using a trained YOLOv8 model.