heart_disease_with_attributions

Explaining a Custom NN Heart Disease Classification Using the Attributions Explainer

This notebook demonstrates how to use the attributions explainer API to explain a Cleveland Heart Disease dataset classification example using a Custom TensorFlow NN.

heart_disease.ipynb performs the following steps:

1. Import dependencies
2. Load and process the Heart Disease CSV file from the TensorFlow data hub
3. Design the TensorFlow NN
4. Train the CNN
5. Visualize the custom NN classifications using kernel_explainer()

Running the notebook

To run heart_disease.ipynb, install the following dependencies:

1. Intel® Explainable AI

References

Heart Disease Dataset - https://archive.ics.uci.edu/ml/datasets/heart+disease