SLIDE 1
Ideas o Ideas on M n Mac achine L hine Lear earning ning In - - PowerPoint PPT Presentation
Ideas o Ideas on M n Mac achine L hine Lear earning ning In - - PowerPoint PPT Presentation
Ideas o Ideas on M n Mac achine L hine Lear earning ning In Inter erpr pretabilit ability Patrick Hall, Wen Phan, SriSatish Ambati and the H2O.ai team Bi Big Ideas Learning from data Adapted from: Learning from Data.
SLIDE 2
SLIDE 3
Learning from data …
Adapted from: Learning from Data. https://work.caltech.edu/textbook.html
SLIDE 4
EXPLAIN HYPOTHESIS
h ≈ g, βj g(x(i)j), g(x(i)(-j))
(explain predictions with reason codes)
Learning from data … transparently.
Adapted from: Learning from Data. https://work.caltech.edu/textbook.html
SLIDE 5
Increasing fairness, accountability, and trust by decreasing unwanted sociological biases
Source: http://money.cnn.com/, Apple Computers
SLIDE 6
Increasing trust by quantifying prediction variance
Source: http://www.vias.org/tmdatanaleng/
SLIDE 7
7
A framework for interpretability
Complexity of learned functions:
- Linear, monotonic
- Nonlinear, monotonic
- Nonlinear, non-monotonic
(~ Number of parameters/VC dimension) Enhancing trust and understanding: the mechanisms and results of an interpretable model should be both transparent AND dependable. Understanding ~ transparency Trust ~ fairness and accountability Scope of interpretability: Global vs. local Application domain: Model-agnostic vs. model-specific
SLIDE 8
Bi Big Ch Challenges
SLIDE 9
Linear Models Strong model locality Usually stable models and explanations Machine Learning Weak model locality Sometimes unstable models and explanations (a.k.a. The Multiplicity of Good Models )
SLIDE 10
Age Number of Purchases Lost profits. Wasted marketing. “For a one unit increase in age, the number
- f purchases increases by 0.8 on average.”
𝑦 = 0.8 𝑦
Linear Models Machine Learning
Exact explanations for approximate models. Approximate explanations for exact models.
Age
“Slope begins to decrease here. Act to
- ptimize savings.”
“Slope begins to increase here sharply. Act to optimize profits.”
Number of Purchase 𝑦 ≈ 𝑔(𝑦)
SLIDE 11
A A Few of
- f Ou
Our Favor
- rite Things
gs
SLIDE 12
Partial dependence plots
Source: http://statweb.stanford.edu/~tibs/ElemStatLearn/printings/ESLII_print10.pdf
HomeValue ~ MedInc + AveOccup + HouseAge + AveRooms
SLIDE 13
Surrogate models
SLIDE 14
Local interpretable model-agnostic explanations
Source: https://www.oreilly.com/learning/introduction-to-local-interpretable-model-agnostic-explanations-lime
SLIDE 15
Variable importance measures
Global variable importance indicates the impact of a variable on the model for the entire training data set. Local variable importance can indicate the impact of a variable for each decision a model makes – similar to reason codes.
SLIDE 16
Re Resources
SLIDE 17
Machine Learning Interpretability with H2O Driverless AI
https://www.h2o.ai/wp-content/uploads/2017/09/MLI.pdf (OR come by the booth!!)
Ideas on Interpreting Machine Learning
https://www.oreilly.com/ideas/ideas-on-interpreting-machine-learning
FAT/ML
http://www.fatml.org/
SLIDE 18