Assemble an efficient interpretable machine learning workflow.

gradient-boosted regression and decision tree models on behavioural animal data (PLOS Computational Biology, doi: https://doi.org/10.1371/journal.pcbi.1011985)

Understanding the limitations of Gassmann's fluid substitution model using explainable ML

Post-hoc analysis of relevant spatiotemporal features for speech decoding using a linear support vector classifier and LDA. The post-hoc analysis is made by using the SHAP technique

This script focuses on explaining a pre-trained CNN’s predictions on the MedMNIST dataset using Deep SHAP. Shapley values are computed for each pixel, summed to create a single Shapley score per image, and saved alongside labels in CSV files for interpretability in medical image classification.