SMS/Email spam prediction machine learning model.
L'objectif de ce challenge est de proposer une méthode de classification, basée sur des réseaux de neurones, permettant de classer des images issues de Google Quickdraw (https://quickdraw.withgoogle.com/data). Le jeu de données proposé comprend 5 classes balancées, avec 15000 exemples d'apprentissage et 5000 exemples de validation.
Comprehensive PyTorch Lightning framework featuring 20+ educational notebooks, advanced ML patterns, and production-ready workflows. Covers vision, NLP, tabular, and time series domains with distributed training, mixed precision, custom loops, and deployment pipelines. Complete with synthetic data generators and testing.
RetenX is a Machine Learning–based Employee Attrition Prediction System that helps organizations identify employees at risk of leaving. It leverages multiple ML models (Random Forest, Logistic Regression, SVM, KNN, XGBoost) to deliver accurate predictions, while offering a clean Flask web interface for ease of use.
A simple machine learning project that predicts loan approval status using a Naive Bayes classifier. Includes data cleaning, model training, evaluation, and prediction steps to demonstrate the full workflow.
Deep learning solution for apple disease detection using CNN architecture. Trained on PlantVillage dataset to classify 4 apple leaf conditions with real-time image analysis.
Machine learning model to predict loan approvals based on applicant financial and personal info
End-to-end implementations of Natural Language Processing (NLP) projects and experiments, featuring sentiment analysis, text preprocessing, and machine learning models.
Verbessern Sie Ihre KI-Modelle durch Fine-Tuning mit dem Toolkit von OpenAI. Erfahren Sie mehr über die Datenaufbereitung, die Trainingsschritte und fortgeschrittene Tuning-Ansätze für eine optimale Leistung.
Landmark based detection model using MediaPipe (Binary classification)
A comprehensive deep learning framework for face recognition model training. Supports mainstream architectures (ArcFace, CosFace, SphereFace) with flexible data pipeline, distributed training, and easy-to-use APIs. Built for researchers and developers to accelerate face recognition model development.
End-to-end Credit Card Fraud Detection project using Python, Scikit-learn, and Streamlit — includes data ingestion, feature engineering, model training, scoring, monitoring, and an interactive dashboard for fraud analysis.
Ultralytics-style train, align, and generate lifecycle API for tiny CPU tests, NeMo AutoModel, and Megatron Bridge.
A collection of mini machine learning projects built to strengthen my ML skills through hands-on practice. Each project focuses on a different machine learning concept, with individual projects uploaded to explore and apply those concepts in practice.
A machine-learning movie recommendation app that suggests similar films using feature similarity and TMDB data, with an interactive Streamlit interface for browsing titles and posters
Détecter les faux billets à partir du jeu de données englobant statistiques sur 6 caracthéristiques des billets
Neural network implementations from scratch
This project contains the file of my undergraduate Final Year Project. This project aims to expose cyberbullying in Twitter by using Machine Learning to classify whether the tweet is suspicious or not. A deployment has been created using streamlit.
ML model training pipeline for the main Spyware Detector project
A portfolio of all of the various Kaggle competitions and projects I have participated in, which mostly revolves around machine learning.
To associate your repository with the model-training topic, visit your repo's landing page and select "manage topics."