Sensitivity analysis uses small peturbations of input data to see how much the output of an algorithm changes. This can be used as part of the system design process, if the output is highly sensitive to certain input fields then it is important that these are collected or measured with high accuracy. Sensitvity analysis is also a central part of several techniques in explainable AI. For example, consider a black box image classification system that uses a deep neural network; by measuring the sensitivity of the classification of an image to each pixel one can create a heat map showing which portions of the image are being used by the network to classify the image.
Used in Chap. 21: pages 335, 337
Also known as sensitivity
Sensitivity analysis using small perturbations of the original data.