Downloaded 105 times
More Related Content
Similar to An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!
- 1. Explainable AI (XAI) Aquick guide to understand how to interpret ML models Mansour Saffar ML Developer - AltaML Inc.
- 2. In the nearfuture... Image source: https://www.scoopnest.com/user/NewYorker/684741246443778048-a-cartoon-by-paul-noth-find-more-cartoons-from- this-week39s-issue-here
- 3. ML Model Categories WhiteBox Models ● Easy to interpret ● Sometimes can not learn the patterns in the data well (low accuracy) due to their simplicity Black Box Models ● Hard (or impossible) to interpret ● Mostly more powerful and effective compared to white box models ○ e.g. neural networks
- 4. Accuracy vs Interpretability Imagesource: https://towardsdatascience.com/interpretability-vs-accuracy-the-friction-that-defines-deep-learning- dae16c84db5c
- 5. What is XAI? Imagesource: https://github.com/LumousAI/Lantern ● Think of XAI as a Lantern inside your ML model ● XAI helps you explain the results of your ML model ● You will know Why and How does your ML model work when you use XAI! XAI Symbol! Note: Actually, I made this symbol up :)
- 6. Some XAI UseCases Image source: https://blog.lifeextension.com/2019/01/machine-learning-and-medicine-is-ai.html https://algorithmxlab.com/blog/the-big-problems-with-machine-learning-algorithms-in-finance/ https://www.forbes.com/sites/bernardmarr/2018/05/23/how-ai-and-machine-learning-are-transforming-law-firms-and-the-legal- sector/#56d5191a32c3 https://datafloq.com/read/machine-learning-drive-autonomous-vehicles/3152 https://www.technologyreview.com/f/612915/chinas-military-is-rushing-to-use-artificial-intelligence/ Medicine Finance Legal Autonomous Cars Military
- 7. Some XAI UseCases Image source: https://blog.lifeextension.com/2019/01/machine-learning-and-medicine-is-ai.html https://algorithmxlab.com/blog/the-big-problems-with-machine-learning-algorithms-in-finance/ https://www.forbes.com/sites/bernardmarr/2018/05/23/how-ai-and-machine-learning-are-transforming-law-firms-and-the-legal- sector/#56d5191a32c3 https://datafloq.com/read/machine-learning-drive-autonomous-vehicles/3152 https://www.technologyreview.com/f/612915/chinas-military-is-rushing-to-use-artificial-intelligence/ Medicine Finance Legal Autonomous Cars Military
- 8. Why do weneed XAI?! (Medical Application) Image sources: https://msaffarm.github.io/projects/ml- mri/Sahebzamani.Saffar.HSZ.Jan.2019.pdf https://artemisinccouk.wordpress.com/author/torak289/ Brain MRI data Complex ML model Report: Patient is diagnosed with Epilepsy with %85 confidence. But why?! Can I trust this prediction? Epilepsy Detection Model with Brain MRI Data
- 9. Why do weneed XAI?! (Finance Application) Image sources: https://artemisinccouk.wordpress.com/author/torak289/ https://www.finder.com/credit-report Financial and Demographic Data Complex ML model Report: Customer is not eligible for the loan! Loan Model with Financial Records But why?!
- 10. XAI to HelpWith Legal Implications Can I trust the epilepsy model predictions? ● General Data Protection Regulation (GDPR) ● GDPR imposes companies to provide exaplanations of their ML models to their customers. ● Legal implication of wrong diagnosis in medical applications can be tough! (of course the human loss is more sad!) ● How can the doctor trust the ML model predictions? What if the customer asks why he was rejected? Image sources: https://www.leaprate.com/financial-services/fines/occ-assesses-70-million-civil-money-penalty- citibank/ https://venturebeat.com/2018/01/27/gdpr-a-playbook-for-compliance/
- 11. XAI General Overview Imagesource: Modified https://github.com/slundberg/shap XAI
- 12. What Answers DoesXAI Provide? ● Why did the model make that prediction? WHY ● How can I correct an error? HOW ● When can I trust ML model predictions? ● When will the ML model fail to make the right prediction? WHEN
- 13. XAI Off vsXAI On! Image source: Modified https://www.darpa.mil/attachments/XAIProgramUpdate.pdf
- 14. What Problems ofML can XAI Address? ● Understand decision making process ● Make sure model is looking at the right features TRUST ● Understand what features are taken into account ● Detect biased patterns in data BIAS & FAIRNESS ● Explain the decision making process EXPLAINABILITY
- 15. XAI Categories Global Explanation ●Explain the behaviour of the ML model in overall Model-Agnostic ● It does not care what the models is and how it works! Local Explanation ● Explain the prediction results for each desired instance Model-Dependant ● Interpretations are based on the model’s learning process
- 16. XAI Categories Global Explanation ●Explain the behaviour of the ML model in overall Model-Agnostic ● It does not care what the models is and how it works! Local Explanation ● Explain the prediction results for each desired instance Model-Dependant ● Interpretations are based on the model’s learning process
- 17. XAI Example 1(Global Explanation) ● Let’s say you have a bike renting business and want to know how much weather affects your business! ● Partial Dependence Plot (PDP) to the rescue ● How change in one attribute (feature) can change your prediction
- 18. XAI Example 2(Global Explanation) ● Let’s say you want to explain the behaviour of a HUGE random forest model ○ 10000 trees! ● Surrogate Model ○ Decision tree
- 19. XAI Example 3(Local Explanation) ● Let’s say you trained a image classification model! ● How does the model know where is the labrador? ● How does the model know there is guitar in the picture? Image sources: https://github.com/marcotcr/lime
- 20. XAI Example 3(Local Explanation) ● Locally Interpretable Model-agnostic Explanations (LIME) Image sources: https://github.com/marcotcr/lime
- 21. Shapley Values ● Let’sshare a ride to AltaML ○ Mansour (Ma) => $40 ○ Mohammad (Mo) => $5 ○ Mina (Mi) => $25 Image sources: https://www.barrieyellowtaxi.com/
- 22. Shapley Values (Ma, Mi,Mo) 40 0 0 (Ma, Mo, Mi) 40 0 0 (Mi, Ma, Mo) 15 0 25 (Mi, Mo, Ma) 15 0 25 (Mo, Mi, Ma) 15 5 20 (Mo, Ma, Mi) 35 5 0 26.66 1.66 11.66 Ma 40 Mo 5 Mi 25 Ma, Mi 40 Ma, Mo 40 Mi, Mo 25 Ma, Mi, Mo 40 Ma Mo Mi
- 23. XAI Example 4(Local Explanation) ● SHAP (SHapley Additive exPlanations) ● It’s idea is based on the Shapley Values in game theory! ● How much each feature contributes to the final prediction ● It’s like the ride sharing example but features are passengers and the amount paid is the model prediction!
- 24. XAI Toolsets andLibraries ● LIME ● SHAP ● Microsoft’s InterpretML ● H2O’s Driverless AI ● Google’s What-If tool ● Tf-explain (Tensorboard) ● IBM Watson
- 25. XAI Future ● Somemodels will be able to explain their results! (think of it as saying ‘Analysis’ to robots in Westworld) ● More interpretable models which you can interact with and modify (or improve) their results ● Debugging ML models will shift more into high-level (semantic level) debugging since you can tell which parts of the model are not functioning properly! ● You might be able to inject your knowledge into the model since it is interpretable and you know how it makes the decision!
- 26. Acknowledgements ● AltaML teamfor their support and constructive feedback
- 27. Thank You! Any Questions? Imagesource: https://killerinnovations.com/what-is-the-innovation-behind-chatbots-and-why-is-it-important-s12-ep5/
- 28. References ● https://github.com/h2oai/mli-resources ● https://www.darpa.mil/program/explainable-artificial-intelligence ●https://christophm.github.io/interpretable-ml-book/ ● https://github.com/marcotcr/lime ● https://github.com/slundberg/shap ● https://github.com/microsoft/interpret