Using LIME To Explain Keras Models

Shirin Glander shows us how to use the LIME package to explain image recognition models built from Keras:

The segmentation of an image into superpixels are an important step in generating explanations for image models. It is both important that the segmentation is correct and follows meaningful patterns in the picture, but also that the size/number of superpixels are appropriate. If the important features in the image are chopped into too many segments the permutations will probably damage the picture beyond recognition in almost all cases leading to a poor or failing explanation model. As the size of the object of interest is varying it is impossible to set up hard rules for the number of superpixels to segment into – the larger the object is relative to the size of the image, the fewer superpixels should be generated. Using plot_superpixels it is possible to evaluate the superpixel parameters before starting the time-consuming explanation function.

Fun stuff.  I’m glad that there’s a lot of work going into explaining neural networks rather than hand-waving them off as magic.

Related Posts

Combining Plots In R With cowplot

Abdul Majed Raja shows how to use the cowplot library in R to merge together independent plots into a single image: The way it works in cowplot is that, we have assign our individual ggplot-plots as an R object (which is by default of type ggplot). These objects are finally used by cowplot to produce […]

Read More

Classifying Texts With Naive Bayes

I continue my series on Naive Bayes with another hand-calculation post: Step two is, on the surface, pretty tough: how do we figure out if a set of words is a business phrase or a baseball phrase? We could try to think up a set of features. For example, how long is the phrase? How many unique […]

Read More

Categories

June 2018
MTWTFSS
« May Jul »
 123
45678910
11121314151617
18192021222324
252627282930