What is machine-learning-projects?

Machine Learning Projects is a curated portfolio of 26 separate machine learning projects built by one developer, covering healthcare AI, computer vision, classical machine learning, natural language processing, time series forecasting, and geospatial data science. According to the README, the collection spans 6 broad domains, includes 5 projects deployed as web apps and 3 as desktop GUI apps, and has attracted over 1.3 thousand stars on GitHub. The healthcare and medical AI section includes six projects such as a brain tumor detector that reads MRI scans with a convolutional neural network and returns a prediction through a Flask web app, a diabetes risk predictor built on the well known Pima Indians dataset, a heart disease predictor claiming around 92 percent accuracy from clinical features, an arrhythmia classifier working from ECG data, a medical chatbot that maps described symptoms to likely diagnoses using natural language processing, and a project predicting how a drug affects biological activity from a Kaggle competition dataset. The computer vision section is the largest, with nine projects including driver drowsiness detection that watches eye movement and sounds an alert, distracted driver detection from dashboard camera images, lane line detection for road video, a person counter using human detection, a face based gender and age predictor, a tool that adds color to black and white photos, a webcam app that automatically snaps a photo when you smile, and an app that overlays a matching emoji on your face based on detected emotion. The README's table of contents also lists sections for classical machine learning and prediction, conversational NLP, time series and business analytics, and geospatial data science, though the specific projects in those sections were not fully shown. Each project lives in its own folder with its own code, and the README links out to a live demo website. The repository is licensed, with license details kept in a separate LICENSE.md file. This project is aimed at students, developers, and anyone learning machine learning who wants working, end to end examples across many different problem types rather than isolated code snippets.