This repo was originally created as a final project for DS340W (Applied Data Sciences).
The purpose of this project is to demonstrate the use of several local and global explainable methods by interpreting the decisions of a number of neural network models, each varying in complexity. Each model is trained using data from the Wisconsin Breast Cancer (Diagnostic) Dataset that can be found here on Kaggle:
https://www.kaggle.com/datasets/uciml/breast-cancer-wisconsin-data
All relevent files are located either within a folder labeled 'dropout' or with 'dropout' specified in the file's name.