Successfully reported this slideshow.
Upcoming SlideShare
×

# Demystifying machine learning using lime

1,456 views

Published on

Slides of my Pycon 2017 short talk "Demystifying machine learning using lime"

Jupyter Notebook with code in https://github.com/albahnsen/Talk_Demystifying_Machine_Learning

Published in: Data & Analytics
• Full Name
Comment goes here.

Are you sure you want to Yes No
• Hello! High Quality And Affordable Essays For You. Starting at \$4.99 per page - Check our website! https://vk.cc/82gJD2

Are you sure you want to  Yes  No

### Demystifying machine learning using lime

1. 1. DEMYSTIFYING MACHINE LEARNING Alejandro Correa Bahnsen 1
2. 2. BLACK BOX MODELS Machine learning models are often dismissed on the grounds of lack of interpretability. When using advanced models it is nearly impossible to understand how a model is making a prediction. 2
3. 3. MNIST - ACCU VS # PARAMS Notebook to create the plot 3
4. 4. 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 LIME 4
5. 5. LIME An interpretable representation is a point in a space whose dimensions can be interpreted by a human. LIME frames the search for an interpretable explanation as an optimization problem. Given a set G of potentially interpretable models, we need a measure L(f,g,x) of how poorly the interpretable model g∈∈G approximates the original model f for point x this is the loss function. We also need some measure Ω(g) of the complexity of the model (e.g. the depth of a decision tree). We then pick a model which minimizes both of these ξ(x) = argmin g∈∈G L(f,g,x)+Ω(g) 5
6. 6. LIME 6
7. 7. LIME EXAMPLE URL PHISHING DETECTION 7
8. 8. URL PHISHING CLASSIFIER Objective: Evaluate phishing probability using only the web site URL 8
9. 9. URL PHISHING CLASSIFIER Train a random forest 9
10. 10. LIME EXAMPLE Fit lime explainer Explain an instance 10
11. 11. LIME EXAMPLE Example Phishing URL Phishing probability 1.0 Url = http://login.paypal.com.convexcentral.com/Update/ab770f624342b07b71e56c1bae5d9bcb/ 11
12. 12. LIME EXAMPLE Example Phishing URL Phishing probability 0.0283 Url = ...http://www.redeyechicago.com/entertainment/tv/redeye-banshee-ivana-mili 12
13. 13. THANK YOU FULL NOTEBOOK IN HTTPS://GITHUB.COM/ALBAHNSEN/TALK _DEMYSTIFYING_MACHINE_LEARNING 13