Portfolio of applied AI capstone projects including medical imaging CNNs and diabetes prediction pipelines.
Explore applied machine learning, medical imaging CNNs, and AI ethics projects.
This repository compiles applied capstone projects across data science, machine learning, and medical imaging. It suits students and developers studying practical neural networks and data pipelines.
It provides structured course folders containing Jupyter notebooks for pneumonia detection using chest X-rays, exploratory data analysis on healthcare datasets, and machine learning pipelines for diabetes prediction. Each folder contains numbered milestones, datasets explanations, and source code.
It suits learners exploring applied deep learning and healthcare data science. It does not suit teams looking for production-ready microservices or enterprise frameworks.
A convolutional neural network trained on chest X-rays with a technical report.
Exploratory data analysis covering cleaning, feature exploration, and correlation.
An end-to-end machine learning workflow predicting diabetes risk from health data.
A humanities capstone examining the societal dimensions of applied AI.
The code is publicly viewable on GitHub, but no open source license is stated in the repository metadata.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
The repository states that the work is protected to prevent unauthorized copying, and asks users not to submit parts of it as their own.
The projects rely on Python, scikit-learn, TensorFlow/Keras, and Pandas.
See Zekai first in Google