Category: Machine Learning

Holger von Jouanne-Diedrich takes us through the intuition of LIME:

There is a new hot area of research to make black-box models interpretable, called Explainable Artificial Intelligence (XAI), if you want to gain some intuition on one such approach (called LIME), read on!

Before we dive right into it it is important to point out when and why you would need interpretability of an AI. While it might be a desirable goal in itself it is not necessary in many fields, at least not for users of an AI, e.g. with text translation, character and speech recognition it is not that important why they do what they do but simply that they work.

In other areas, like medical applications (determining whether tissue is malignant), financial applications (granting a loan to a customer) or applications in the criminal-justice system (gauging the risk of recidivism) it is of the utmost importance (and sometimes even required by law) to know why the machine arrived at its conclusions.

One approach to make AI models explainable is called LIME for Local Interpretable Model-Agnostic Explanations. There is already a lot in this name!

LIME is not trivial to use and it can be very slow, but it is a great way to visualize models.

Abhijit Telang takes us through the calculations involved in Support Vector Machines and then gives us an example in R:

So, let’s take that out and we are back to old, classical vector algebra. It’s like a person with a bunch of sticks to figure out which one to lay where in a 2-D plane to separate one class of objects from another, provided class definitions are already known. 

The problem is which particular shape and length must be chosen to show maximum contrast between classes.

We need to arrive at a function definition, in such a way that the value a given function takes changes drastically (e.g. from a large positive value to a large negative value).

SVM is often great for two-class classification problems, and different variants also work well for multi-class problems.