Greg Schreiter

U of M Bootcamp Final Project

As part of a team, I developed a machine learning model to predict diabetes diagnoses with up to 97% accuracy. This model analyzes patient health metrics such as gender, age, BMI, and blood glucose levels to identify potential diabetes cases. My primary contributions included building and evaluating Support Vector Machine (SVM), deep learning, and advanced decision tree models.

GitHub Repo

Hands-on Machine Learning (3e) Code Replication

Following along with the code examples provided in Hands-on Machine Learning (3e) book by Aurélien Géron. I am reproducing the notebooks, making sure everything runs on my own system, and am adding my own examples where needed. Highlights include chapters on Convolutional Neural Networks, Recurrent Neural Networks, and general Deep Learning best practices.

GitHub Repo

Medical Image Classification with Convolutional Neural Networks

Collaboration with Christine Jauregui

We built a convolutional neural network (CNN) to classify chest CT scans for cancer detection. We trained a CNN from scratch and then explored transfer learning by leveraging pre-trained models to improve performance. Additionally, we investigated the potential benefits and drawbacks of using model ensembles for this task.

GitHub Repo