Download as PDF, PPTX
Uploaded byAlejandro Correa Bahnsen, PhD
Demystifying machine learning using lime
The document discusses the challenges of interpretability in machine learning models, particularly focusing on black box models. It introduces LIME (Local Interpretable Model-Agnostic Explanations) as a method to provide interpretable explanations for any classifier's predictions. An example of using LIME for a URL phishing detection classifier is provided, illustrating how it can evaluate and explain phishing probabilities based on website URLs.
More Related Content
Similar to Demystifying machine learning using lime
Demystifying machine learning using lime
- 1.
- 2. BLACK BOX MODELS Machine learningmodels 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. MNIST - ACCUVS # PARAMS Notebook to create the plot 3
- 4. LIME stands for Local InterpretableModel- agnostic Explanations, and its objective is to explain the result from any classifier so that a human can understand individual predictions LIME 4
- 5. LIME An interpretable representationis 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.
- 7. LIME EXAMPLE URL PHISHINGDETECTION 7
- 8. URL PHISHING CLASSIFIER Objective:Evaluate phishing probability using only the web site URL 8
- 9. URL PHISHING CLASSIFIER Traina random forest 9
- 10. LIME EXAMPLE Fit limeexplainer Explain an instance 10
- 11. LIME EXAMPLE Example PhishingURL Phishing probability 1.0 Url = http://login.paypal.com.convexcentral.com/Update/ab770f624342b07b71e56c1bae5d9bcb/ 11
- 12. LIME EXAMPLE Example PhishingURL Phishing probability 0.0283 Url = ...http://www.redeyechicago.com/entertainment/tv/redeye-banshee-ivana-mili 12
- 13. THANK YOU FULL NOTEBOOKIN HTTPS://GITHUB.COM/ALBAHNSEN/TALK _DEMYSTIFYING_MACHINE_LEARNING 13