Skip to content
master
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.

README.md

Short Talk - Demystifying machine learning using lime

Machine learning models are often dismissed on the grounds of lack of interpretability. There is a popular story about modern algorithms that goes as follows: Simple linear statistical models such as logistic regression yield to interpretable models, on the other hand, advanced models such as random forest or deep neural networks are black boxes. Meaning that it is nearly impossible to understand how a model is making a prediction.

In this talk I present a case study of the LIME model. LIME stands for Local Interpretable Model-agnostic Explanations, and its objective is to explain the result from any classifier so that a human can understand individual predictions.

Notebook

Slides of this talk

About

Pycon.co lightning talk "Demystifying Machine Learning"

Resources

Releases

No releases published

Packages

No packages published
You can’t perform that action at this time.