LIME

Explore how LIME approximates complex neural network predictions locally using linear regression to generate saliency maps. Understand its model-agnostic approach and see practical implementation with visual examples. Gain insights into strengths and limitations of LIME for interpreting deep learning classifiers.

We'll cover the following...

Local interpretable model-agnostic explanations
Implementation of the LIME model

Local interpretable model-agnostic explanations

Local interpretable model-agnostic explanations (LIME) is a technique that can explain the predictions of any classifier or regressor by approximating it locally with an interpretable model. It modifies a single data sample by tweaking the feature values and observes the resulting impact on the output. The output of LIME is a saliency map representing the contribution of each feature to the prediction.

Given a data point $X$ , a neural network $f(.)$ can be written as a linear function in the local neighborhood of $X$ . In other words:

1.Introduction to Explainable AI

Project

2.Saliency Maps

3.Class Activation Maps

4.Miscellaneous Methods

5.Metrics of Interpretability

Assessment

Mini Project

LIME

Local interpretable model-agnostic explanations