SlideShare a Scribd company logo
1 of 37
Download to read offline
Towards human centered
machine learning (ML)
Oct 2019
Kansas City
Bahador Khaleghi
Customer Data Scientist
bahador.khaleghi@h2o.ai
Outline
The promises and perils of ML
The need for human centered ML
The case for ML explainability (why and what)
The how of ML explainability
ML explainability at H2O.ai
2
The promises of ML
Recognize complex patterns in big structured data
- Customer churn prediction, fraud detection
Basic perception of unstructured data
- Computer vision: object detection, object recognition
- Natural language processing: sentiment analysis, document classification, automatic translation
- Speech recognition: voice command, automated answering system
See into the future
- Time series forecasting: predictive maintenance 3
The perils of ML
ML technology has been evolving too fast
Unethical/irresponsible usage of ML can threaten our basic
human rights
Regulatory bodies are left behind, thus many regulatory
gaps
ML community has been mainly focused on performance
until recently
4
https://blog-sap.com/analytics/files/2017/07/7.27.ageofacclerations.png
5
https://medium.com/@AINowInstitute/ai-in-2018-a-year-in-review-8b161ead2b4e
Human centered ML to the rescue?*
Key idea: humans should ultimately be in control of ML technology
Develop ML technology with humans in mind so that it is
- Useful
- Trustworthy
- Congruent with our social values
6
* https://www.linkedin.com/pulse/human-centered-ai-building-humans-mind-rachel-samson/
Ethics ML
HCI
Challenges of trustworthy ML
7https://medium.com/element-ai-research-lab/a-taxonomy-of-ai-trustability-challenges-1c68f160d027
ML explanations can facilitate other aspects of trust
- Flag potential model bias
- e.g.: are protected features acting as the main predictors?
- Accountability
- e.g.: what caused an autonomous car’s pedestrian detector to fail?
- Robustness
- e.g.: models that rely on explainable features tend to be more resilient to adversarial attacks
Importance of ML explainability
8
Why ML explainability?
Regulatory compliance
- Customers in regulated industries like banking and
insurance need/want MLI
- Equal Credit Opportunity Act (ECOA) in US
- GDPR in EU and the “right to explanation” argument
- Security audit
Can help identify issues with an otherwise (seemingly)
performant model
- The case of husky misclassified as wolf
https://arxiv.org/abs/1602.04938
9
What does it mean to explain a model?*
Main question: what drove prediction(s) of a model?
Answer: depends!
- Who is asking: e.g. model creator vs examiner
- Many explanation families
- Importance scores
- Decision trees/rules
- Dependency plots
- Counterfactual
- Verbal
- ...
10
*https://www.elementai.com/news/2019/the-what-of-explainable-ai
The How of ML explainability*
11*https://towardsdatascience.com/the-how-of-explainable-ai-pre-modelling-explainability-699150495fe4
Pre-modelling explanations*
Exploratory data analysis and visualization
Dataset description standardization
Dataset summarization
Explainable feature engineering
12*https://towardsdatascience.com/the-how-of-explainable-ai-pre-modelling-explainability-699150495fe4
Explainable modelling*
Alleged explainability vs performance
tradeoff
Many potential ways to beat that
- Joint prediction and explanation
- Hybrid models
- Explainability through regularization
- ...
13*https://towardsdatascience.com/the-how-of-explainable-ai-explainable-modelling-55c8c43d7bed
Extracting (post-hoc) explanations*
The main focus of the research
community
Many explaining deep neural
networks
Estimator mechanisms
- Input perturbation
- Backward propagation
- Proxy
- Activation maximization
14*https://towardsdatascience.com/the-how-of-explainable-ai-post-modelling-explainability-8b4cbc7adf5f
ML explainability at H2O.ai
We are one of the pioneers of ML explainability in industry
Work closely with our clients and regulatory bodies to establish
best practices
Incorporated explainability capabilities into our products back
in 2016
- Machine learning interpretability (MLI)
15
Overview of our products
16
Driverless AI (DAI): How it works
17
What is MLI?
Stands for Machine Learning
Interpretability
A (separate) pipeline within
DAI that provides a set of
features aimed at explaining
output of DAI models
Can also be applied to models
developed outside DAI
18
MLI’s local explanations
How a row prediction came about?
Feature importance Decision logic Prediction behavior
when varying a feature
Exact SHAP NA ICE on DAI model
Approximate LIME, LOCO DT surrogate ICE on RF surrogate
19
Key idea & Approach: approximate response function of a
complex model locally with a (weighted) linear model
Pros:
- Easy to implement
- Versatile
Cons:
- Rather costly to compute
- May not work for highly non-linear models => use SHAP
instead
LIME: Linear Interpretable Model-agnostic Explanation
https://arxiv.org/abs/1602.04938
20
SHAP
Key idea: explain prediction as a game played by feature values
Approach: compute the expected contribution of each feature value across all possible feature coalitions
Pros:
- Based on solid math (Shapley values theory)
- Gives exact marginal contribution of each feature to model prediction
Cons:
- Costly to compute in general (has a fast implementation for tree based models)
https://arxiv.org/abs/1705.07874
21
Surrogate Decision Tree (DT)
A single decision tree is trained on the original
inputs and predictions of the DAI model
- Meant to capture the decision making logic
of DAI model to some extent
- Useful for identifying potential feature
interactions
22
Surrogate Random Forest (RF)
Trained similar to surrogate DT
- Provides the global feature
importance scores (also used by
K-LIME clustering)
- Used by LOCO to provide an
alternative local feature importance to
LIME
- Used by approximate PDP and ICE
plots
23
LOCO: Leave One Covariate Out
Key idea: feature importance as the difference in model prediction with and without a given feature
Approach: approximate prediction without a feature using RF surrogate where contributions of rules
involving that feature are removed
Pros:
- Nonlinear and considers feature interactions => alternative to LIME approximate local
explanations
Cons:
- Difficult to generate a mathematical error rate (unlike LIME) 24
ICE: Individual Conditional Expectation
How a row prediction varies if ONLY a desired feature varies
within its domain?
Help explore if the treatment of a specific row is valid in
comparison to
- Average model behavior (PDP) => discrepancies could
reveal possible feature interaction => examine
surrogate DT
- Known standards
- Domain knowledge, and reasonable expectations
ICE PDP
25
MLI’s global explanations
How all (set of) model predictions came about? (what drives model predictions in general)
Feature importance Decision logic Prediction behavior
when varying a feature
Exact Aggregated SHAP NA PDP on DAI model
Approximate K-LIME , RF surrogate,
Aggregated LOCO?
DT surrogate PDP on RF surrogate
26
Key idea: response function of a complex model may
not be linear globally but it could be piecewise linear
Approach: use GLMs to approximate global response
of a complex model within local regions (clusters)
obtained by:
- K-Means applied to the globally most
important features provided by RF surrogate
model
- Decision tree surrogate leafs (LIME-SUP)
- An (optional) clustering column provided by
customer (based on their domain knowledge)
K-LIME
27
PDP: Partial Dependence Plot
How model predictions vary on average if ONLY a desired feature varies within its domain?
Basically aggregate of ICE plots for a given feature
Help explore if overall treatment of a specific feature is valid in comparison to
- Known standards
- Domain knowledge, and reasonable expectations
Feature interactions might be averaged out by PDP
28
Reason codes
A plain English “translation” of K-LIME explanations
Three different scopes: global, cluster, and local
- Local reason codes come with std dev
Also generated for feature contributions provided by
SHAP (not shown in UI by downloadable as a CSV)
29
MLI’s time series explanations
Based on SHAP
DAI might split time series data into multiple
groups when modelling
SHAP explanations are obtained for all
forecasts in each group and aggregated up
30
Evaluating explanations
SHAP explanation should be accurate and consistent, at least in theory
Goodness of fit in case of approximate (surrogate) models
- R2 and RMSE of training and validation data
- Surrogate prediction accuracy
- Ranked predictions plot for K-LIME
Standard deviation in case of PDP, ICE plots, and reason codes
Consistency between different explanation techniques (use MLI dashboard)
http://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/interpret-non-ts.html#expectations-for-consistency-between-e
xplanatory-techniques
31
Assess model’s group fairness through Disparate
Impact Analysis (DIA)
- For a given feature, e.g. sex, compute
average, per group, performance metrics,
e.g. accuracy
- Compute group disparities as the ratio of
group metrics to given reference metric
- Flag cases where group disparities are
beyond the preset thresholds as biased
MLI’s fairness assessment
32
Available for binary classification and regression models
Could be used for model debugging too, e.g. examine confusion matrix and group metrics of
non-protected features
Best suited for constrained models (linear, constrained GBM, RuleFit) as the average group metrics
reported by DIA is less likely to miss cases of local discrimination
MLI’s fairness assessment (cont.)
33
Useful MLI resources
MLI cheat sheet video by PH (Oct 2018): https://www.youtube.com/watch?v=5jSU3CUReXY
MLI Tutorial: https://h2oai.github.io/tutorials/automatic-ml-intro-tutorial/#9
MLI Booklet (May 2019):
http://artifacts.h2o.ai.s3.amazonaws.com/releases/ai/h2o/dai/rel-1.6.2-9/docs/booklets/MLIBooklet.pdf
34
LIME: https://www.oreilly.com/learning/introduction-to-local-interpretable-model-agnostic-explanations-lime
SHAP:
https://towardsdatascience.com/one-feature-attribution-method-to-supposedly-rule-them-all-shapley-values-f3e04534983d
PDP: https://christophm.github.io/interpretable-ml-book/pdp.html
ICE: https://christophm.github.io/interpretable-ml-book/ice.html
LOCO: http://www.stat.cmu.edu/~ryantibs/papers/conformal.pdf
LIME-SUP: https://arxiv.org/pdf/1806.00663.pdf
Learn more
35
The what of explainable AI: https://www.elementai.com/news/2019/the-what-of-explainable-ai
The why of explainable AI: https://www.elementai.com/news/2019/the-why-of-explainable-ai
The how of explainable AI- pre-modelling explainability:
https://towardsdatascience.com/the-how-of-explainable-ai-pre-modelling-explainability-699150495fe4
The how of explainable AI- explainable modelling:
https://towardsdatascience.com/the-how-of-explainable-ai-explainable-modelling-55c8c43d7bed
The how of explainable AI- post-modelling explainability:
https://towardsdatascience.com/the-how-of-explainable-ai-post-modelling-explainability-8b4cbc7adf5f
Learn more
36
Q&A
37

More Related Content

What's hot

Generative Models and ChatGPT
Generative Models and ChatGPTGenerative Models and ChatGPT
Generative Models and ChatGPTLoic Merckel
 
Explainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableExplainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableAditya Bhattacharya
 
DC02. Interpretation of predictions
DC02. Interpretation of predictionsDC02. Interpretation of predictions
DC02. Interpretation of predictionsAnton Kulesh
 
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...David Talby
 
Explainable AI in Industry (FAT* 2020 Tutorial)
Explainable AI in Industry (FAT* 2020 Tutorial)Explainable AI in Industry (FAT* 2020 Tutorial)
Explainable AI in Industry (FAT* 2020 Tutorial)Krishnaram Kenthapadi
 
AI in IoT: Use Cases and Challenges
AI in IoT: Use Cases and ChallengesAI in IoT: Use Cases and Challenges
AI in IoT: Use Cases and ChallengesDmitry Petukhov
 
Large Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfLarge Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfDavid Rostcheck
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEDatabricks
 
Automated Machine Learning
Automated Machine LearningAutomated Machine Learning
Automated Machine LearningYuriy Guts
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Krishnaram Kenthapadi
 
Unlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfUnlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfPremNaraindas1
 
Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)GoDataDriven
 
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1DianaGray10
 
Automated Machine Learning (Auto ML)
Automated Machine Learning (Auto ML)Automated Machine Learning (Auto ML)
Automated Machine Learning (Auto ML)Hayim Makabee
 
Generative AI in Healthcare Market.pptx
Generative AI in Healthcare Market.pptxGenerative AI in Healthcare Market.pptx
Generative AI in Healthcare Market.pptxGayatriGadhave1
 
The Next Big Thing in AI - Causality
The Next Big Thing in AI - CausalityThe Next Big Thing in AI - Causality
The Next Big Thing in AI - CausalityVaticle
 
And then there were ... Large Language Models
And then there were ... Large Language ModelsAnd then there were ... Large Language Models
And then there were ... Large Language ModelsLeon Dohmen
 

What's hot (20)

Generative Models and ChatGPT
Generative Models and ChatGPTGenerative Models and ChatGPT
Generative Models and ChatGPT
 
Explainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableExplainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretable
 
DC02. Interpretation of predictions
DC02. Interpretation of predictionsDC02. Interpretation of predictions
DC02. Interpretation of predictions
 
AI in healthcare - Use Cases
AI in healthcare - Use Cases AI in healthcare - Use Cases
AI in healthcare - Use Cases
 
Explainable AI (XAI)
Explainable AI (XAI)Explainable AI (XAI)
Explainable AI (XAI)
 
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
 
Explainable AI in Industry (FAT* 2020 Tutorial)
Explainable AI in Industry (FAT* 2020 Tutorial)Explainable AI in Industry (FAT* 2020 Tutorial)
Explainable AI in Industry (FAT* 2020 Tutorial)
 
AI in IoT: Use Cases and Challenges
AI in IoT: Use Cases and ChallengesAI in IoT: Use Cases and Challenges
AI in IoT: Use Cases and Challenges
 
Large Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdfLarge Language Models - Chat AI.pdf
Large Language Models - Chat AI.pdf
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
 
Automated Machine Learning
Automated Machine LearningAutomated Machine Learning
Automated Machine Learning
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)
 
Unlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfUnlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdf
 
Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)
 
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
 
Automated Machine Learning (Auto ML)
Automated Machine Learning (Auto ML)Automated Machine Learning (Auto ML)
Automated Machine Learning (Auto ML)
 
Generative AI in Healthcare Market.pptx
Generative AI in Healthcare Market.pptxGenerative AI in Healthcare Market.pptx
Generative AI in Healthcare Market.pptx
 
The Next Big Thing in AI - Causality
The Next Big Thing in AI - CausalityThe Next Big Thing in AI - Causality
The Next Big Thing in AI - Causality
 
Responsible AI
Responsible AIResponsible AI
Responsible AI
 
And then there were ... Large Language Models
And then there were ... Large Language ModelsAnd then there were ... Large Language Models
And then there were ... Large Language Models
 

Similar to Towards Human-Centered Machine Learning

Practical machine learning
Practical machine learningPractical machine learning
Practical machine learningFaizan Javed
 
mapReduce for machine learning
mapReduce for machine learning mapReduce for machine learning
mapReduce for machine learning Pranya Prabhakar
 
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!Sri Ambati
 
ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case
ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case
ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case eProsima
 
Studying Software Engineering Patterns for Designing Machine Learning Systems
Studying Software Engineering Patterns for Designing Machine Learning SystemsStudying Software Engineering Patterns for Designing Machine Learning Systems
Studying Software Engineering Patterns for Designing Machine Learning SystemsHironori Washizaki
 
Model-Based Systems Engineering Demystified
Model-Based Systems Engineering DemystifiedModel-Based Systems Engineering Demystified
Model-Based Systems Engineering DemystifiedElizabeth Steiner
 
From Model-based to Model and Simulation-based Systems Architectures
From Model-based to Model and Simulation-based Systems ArchitecturesFrom Model-based to Model and Simulation-based Systems Architectures
From Model-based to Model and Simulation-based Systems ArchitecturesObeo
 
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.ai
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.aiPractical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.ai
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.aiSri Ambati
 
Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...
Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...
Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...Willy Marroquin (WillyDevNET)
 
Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SF
Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SFTed Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SF
Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SFMLconf
 
MLSEV Virtual. ML Platformization and AutoML in the Enterprise
MLSEV Virtual. ML Platformization and AutoML in the EnterpriseMLSEV Virtual. ML Platformization and AutoML in the Enterprise
MLSEV Virtual. ML Platformization and AutoML in the EnterpriseBigML, Inc
 
Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...
Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...
Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...Ed Fernandez
 
Interpretable Machine Learning
Interpretable Machine LearningInterpretable Machine Learning
Interpretable Machine LearningSri Ambati
 
Generalized Linear Models with H2O
Generalized Linear Models with H2O Generalized Linear Models with H2O
Generalized Linear Models with H2O Sri Ambati
 
Designing a Generative AI QnA solution with Proprietary Enterprise Business K...
Designing a Generative AI QnA solution with Proprietary Enterprise Business K...Designing a Generative AI QnA solution with Proprietary Enterprise Business K...
Designing a Generative AI QnA solution with Proprietary Enterprise Business K...IRJET Journal
 
Big learning 1.2
Big learning   1.2Big learning   1.2
Big learning 1.2Mohit Garg
 

Similar to Towards Human-Centered Machine Learning (20)

Practical machine learning
Practical machine learningPractical machine learning
Practical machine learning
 
mapReduce for machine learning
mapReduce for machine learning mapReduce for machine learning
mapReduce for machine learning
 
Wims2012
Wims2012Wims2012
Wims2012
 
24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)
24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)
24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)
 
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
 
ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case
ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case
ROS 2 AI Integration Working Group 1: ALMA, SustainML & ROS 2 use case
 
Studying Software Engineering Patterns for Designing Machine Learning Systems
Studying Software Engineering Patterns for Designing Machine Learning SystemsStudying Software Engineering Patterns for Designing Machine Learning Systems
Studying Software Engineering Patterns for Designing Machine Learning Systems
 
Model-Based Systems Engineering Demystified
Model-Based Systems Engineering DemystifiedModel-Based Systems Engineering Demystified
Model-Based Systems Engineering Demystified
 
From Model-based to Model and Simulation-based Systems Architectures
From Model-based to Model and Simulation-based Systems ArchitecturesFrom Model-based to Model and Simulation-based Systems Architectures
From Model-based to Model and Simulation-based Systems Architectures
 
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.ai
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.aiPractical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.ai
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.ai
 
Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...
Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...
Deep Learning for Real-Time Atari Game Play Using Offline Monte-CarloTree Sear...
 
Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SF
Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SFTed Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SF
Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel at MLconf SF
 
MLSEV Virtual. ML Platformization and AutoML in the Enterprise
MLSEV Virtual. ML Platformization and AutoML in the EnterpriseMLSEV Virtual. ML Platformization and AutoML in the Enterprise
MLSEV Virtual. ML Platformization and AutoML in the Enterprise
 
Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...
Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...
Machine Learning Platformization & AutoML: Adopting ML at Scale in the Enterp...
 
Iwesep19.ppt
Iwesep19.pptIwesep19.ppt
Iwesep19.ppt
 
System mldl meetup
System mldl meetupSystem mldl meetup
System mldl meetup
 
Interpretable Machine Learning
Interpretable Machine LearningInterpretable Machine Learning
Interpretable Machine Learning
 
Generalized Linear Models with H2O
Generalized Linear Models with H2O Generalized Linear Models with H2O
Generalized Linear Models with H2O
 
Designing a Generative AI QnA solution with Proprietary Enterprise Business K...
Designing a Generative AI QnA solution with Proprietary Enterprise Business K...Designing a Generative AI QnA solution with Proprietary Enterprise Business K...
Designing a Generative AI QnA solution with Proprietary Enterprise Business K...
 
Big learning 1.2
Big learning   1.2Big learning   1.2
Big learning 1.2
 

More from Sri Ambati

H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
Generative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptxGenerative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptxSri Ambati
 
AI and the Future of Software Development: A Sneak Peek
AI and the Future of Software Development: A Sneak Peek AI and the Future of Software Development: A Sneak Peek
AI and the Future of Software Development: A Sneak Peek Sri Ambati
 
LLMOps: Match report from the top of the 5th
LLMOps: Match report from the top of the 5thLLMOps: Match report from the top of the 5th
LLMOps: Match report from the top of the 5thSri Ambati
 
Building, Evaluating, and Optimizing your RAG App for Production
Building, Evaluating, and Optimizing your RAG App for ProductionBuilding, Evaluating, and Optimizing your RAG App for Production
Building, Evaluating, and Optimizing your RAG App for ProductionSri Ambati
 
Building LLM Solutions using Open Source and Closed Source Solutions in Coher...
Building LLM Solutions using Open Source and Closed Source Solutions in Coher...Building LLM Solutions using Open Source and Closed Source Solutions in Coher...
Building LLM Solutions using Open Source and Closed Source Solutions in Coher...Sri Ambati
 
Risk Management for LLMs
Risk Management for LLMsRisk Management for LLMs
Risk Management for LLMsSri Ambati
 
Open-Source AI: Community is the Way
Open-Source AI: Community is the WayOpen-Source AI: Community is the Way
Open-Source AI: Community is the WaySri Ambati
 
Building Custom GenAI Apps at H2O
Building Custom GenAI Apps at H2OBuilding Custom GenAI Apps at H2O
Building Custom GenAI Apps at H2OSri Ambati
 
Applied Gen AI for the Finance Vertical
Applied Gen AI for the Finance Vertical Applied Gen AI for the Finance Vertical
Applied Gen AI for the Finance Vertical Sri Ambati
 
Cutting Edge Tricks from LLM Papers
Cutting Edge Tricks from LLM PapersCutting Edge Tricks from LLM Papers
Cutting Edge Tricks from LLM PapersSri Ambati
 
Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...
Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...
Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...Sri Ambati
 
Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...
Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...
Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...Sri Ambati
 
KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...
KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...
KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...Sri Ambati
 
LLM Interpretability
LLM Interpretability LLM Interpretability
LLM Interpretability Sri Ambati
 
Never Reply to an Email Again
Never Reply to an Email AgainNever Reply to an Email Again
Never Reply to an Email AgainSri Ambati
 
Introducción al Aprendizaje Automatico con H2O-3 (1)
Introducción al Aprendizaje Automatico con H2O-3 (1)Introducción al Aprendizaje Automatico con H2O-3 (1)
Introducción al Aprendizaje Automatico con H2O-3 (1)Sri Ambati
 
From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...
From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...
From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...Sri Ambati
 
AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...
AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...
AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...Sri Ambati
 
AI Foundations Course Module 1 - An AI Transformation Journey
AI Foundations Course Module 1 - An AI Transformation JourneyAI Foundations Course Module 1 - An AI Transformation Journey
AI Foundations Course Module 1 - An AI Transformation JourneySri Ambati
 

More from Sri Ambati (20)

H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
Generative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptxGenerative AI Masterclass - Model Risk Management.pptx
Generative AI Masterclass - Model Risk Management.pptx
 
AI and the Future of Software Development: A Sneak Peek
AI and the Future of Software Development: A Sneak Peek AI and the Future of Software Development: A Sneak Peek
AI and the Future of Software Development: A Sneak Peek
 
LLMOps: Match report from the top of the 5th
LLMOps: Match report from the top of the 5thLLMOps: Match report from the top of the 5th
LLMOps: Match report from the top of the 5th
 
Building, Evaluating, and Optimizing your RAG App for Production
Building, Evaluating, and Optimizing your RAG App for ProductionBuilding, Evaluating, and Optimizing your RAG App for Production
Building, Evaluating, and Optimizing your RAG App for Production
 
Building LLM Solutions using Open Source and Closed Source Solutions in Coher...
Building LLM Solutions using Open Source and Closed Source Solutions in Coher...Building LLM Solutions using Open Source and Closed Source Solutions in Coher...
Building LLM Solutions using Open Source and Closed Source Solutions in Coher...
 
Risk Management for LLMs
Risk Management for LLMsRisk Management for LLMs
Risk Management for LLMs
 
Open-Source AI: Community is the Way
Open-Source AI: Community is the WayOpen-Source AI: Community is the Way
Open-Source AI: Community is the Way
 
Building Custom GenAI Apps at H2O
Building Custom GenAI Apps at H2OBuilding Custom GenAI Apps at H2O
Building Custom GenAI Apps at H2O
 
Applied Gen AI for the Finance Vertical
Applied Gen AI for the Finance Vertical Applied Gen AI for the Finance Vertical
Applied Gen AI for the Finance Vertical
 
Cutting Edge Tricks from LLM Papers
Cutting Edge Tricks from LLM PapersCutting Edge Tricks from LLM Papers
Cutting Edge Tricks from LLM Papers
 
Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...
Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...
Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...
 
Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...
Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...
Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...
 
KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...
KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...
KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...
 
LLM Interpretability
LLM Interpretability LLM Interpretability
LLM Interpretability
 
Never Reply to an Email Again
Never Reply to an Email AgainNever Reply to an Email Again
Never Reply to an Email Again
 
Introducción al Aprendizaje Automatico con H2O-3 (1)
Introducción al Aprendizaje Automatico con H2O-3 (1)Introducción al Aprendizaje Automatico con H2O-3 (1)
Introducción al Aprendizaje Automatico con H2O-3 (1)
 
From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...
From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...
From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...
 
AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...
AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...
AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...
 
AI Foundations Course Module 1 - An AI Transformation Journey
AI Foundations Course Module 1 - An AI Transformation JourneyAI Foundations Course Module 1 - An AI Transformation Journey
AI Foundations Course Module 1 - An AI Transformation Journey
 

Recently uploaded

Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAndikSusilo4
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Hyundai Motor Group
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 

Recently uploaded (20)

Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & Application
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 

Towards Human-Centered Machine Learning

  • 1. Towards human centered machine learning (ML) Oct 2019 Kansas City Bahador Khaleghi Customer Data Scientist bahador.khaleghi@h2o.ai
  • 2. Outline The promises and perils of ML The need for human centered ML The case for ML explainability (why and what) The how of ML explainability ML explainability at H2O.ai 2
  • 3. The promises of ML Recognize complex patterns in big structured data - Customer churn prediction, fraud detection Basic perception of unstructured data - Computer vision: object detection, object recognition - Natural language processing: sentiment analysis, document classification, automatic translation - Speech recognition: voice command, automated answering system See into the future - Time series forecasting: predictive maintenance 3
  • 4. The perils of ML ML technology has been evolving too fast Unethical/irresponsible usage of ML can threaten our basic human rights Regulatory bodies are left behind, thus many regulatory gaps ML community has been mainly focused on performance until recently 4 https://blog-sap.com/analytics/files/2017/07/7.27.ageofacclerations.png
  • 6. Human centered ML to the rescue?* Key idea: humans should ultimately be in control of ML technology Develop ML technology with humans in mind so that it is - Useful - Trustworthy - Congruent with our social values 6 * https://www.linkedin.com/pulse/human-centered-ai-building-humans-mind-rachel-samson/ Ethics ML HCI
  • 7. Challenges of trustworthy ML 7https://medium.com/element-ai-research-lab/a-taxonomy-of-ai-trustability-challenges-1c68f160d027
  • 8. ML explanations can facilitate other aspects of trust - Flag potential model bias - e.g.: are protected features acting as the main predictors? - Accountability - e.g.: what caused an autonomous car’s pedestrian detector to fail? - Robustness - e.g.: models that rely on explainable features tend to be more resilient to adversarial attacks Importance of ML explainability 8
  • 9. Why ML explainability? Regulatory compliance - Customers in regulated industries like banking and insurance need/want MLI - Equal Credit Opportunity Act (ECOA) in US - GDPR in EU and the “right to explanation” argument - Security audit Can help identify issues with an otherwise (seemingly) performant model - The case of husky misclassified as wolf https://arxiv.org/abs/1602.04938 9
  • 10. What does it mean to explain a model?* Main question: what drove prediction(s) of a model? Answer: depends! - Who is asking: e.g. model creator vs examiner - Many explanation families - Importance scores - Decision trees/rules - Dependency plots - Counterfactual - Verbal - ... 10 *https://www.elementai.com/news/2019/the-what-of-explainable-ai
  • 11. The How of ML explainability* 11*https://towardsdatascience.com/the-how-of-explainable-ai-pre-modelling-explainability-699150495fe4
  • 12. Pre-modelling explanations* Exploratory data analysis and visualization Dataset description standardization Dataset summarization Explainable feature engineering 12*https://towardsdatascience.com/the-how-of-explainable-ai-pre-modelling-explainability-699150495fe4
  • 13. Explainable modelling* Alleged explainability vs performance tradeoff Many potential ways to beat that - Joint prediction and explanation - Hybrid models - Explainability through regularization - ... 13*https://towardsdatascience.com/the-how-of-explainable-ai-explainable-modelling-55c8c43d7bed
  • 14. Extracting (post-hoc) explanations* The main focus of the research community Many explaining deep neural networks Estimator mechanisms - Input perturbation - Backward propagation - Proxy - Activation maximization 14*https://towardsdatascience.com/the-how-of-explainable-ai-post-modelling-explainability-8b4cbc7adf5f
  • 15. ML explainability at H2O.ai We are one of the pioneers of ML explainability in industry Work closely with our clients and regulatory bodies to establish best practices Incorporated explainability capabilities into our products back in 2016 - Machine learning interpretability (MLI) 15
  • 16. Overview of our products 16
  • 17. Driverless AI (DAI): How it works 17
  • 18. What is MLI? Stands for Machine Learning Interpretability A (separate) pipeline within DAI that provides a set of features aimed at explaining output of DAI models Can also be applied to models developed outside DAI 18
  • 19. MLI’s local explanations How a row prediction came about? Feature importance Decision logic Prediction behavior when varying a feature Exact SHAP NA ICE on DAI model Approximate LIME, LOCO DT surrogate ICE on RF surrogate 19
  • 20. Key idea & Approach: approximate response function of a complex model locally with a (weighted) linear model Pros: - Easy to implement - Versatile Cons: - Rather costly to compute - May not work for highly non-linear models => use SHAP instead LIME: Linear Interpretable Model-agnostic Explanation https://arxiv.org/abs/1602.04938 20
  • 21. SHAP Key idea: explain prediction as a game played by feature values Approach: compute the expected contribution of each feature value across all possible feature coalitions Pros: - Based on solid math (Shapley values theory) - Gives exact marginal contribution of each feature to model prediction Cons: - Costly to compute in general (has a fast implementation for tree based models) https://arxiv.org/abs/1705.07874 21
  • 22. Surrogate Decision Tree (DT) A single decision tree is trained on the original inputs and predictions of the DAI model - Meant to capture the decision making logic of DAI model to some extent - Useful for identifying potential feature interactions 22
  • 23. Surrogate Random Forest (RF) Trained similar to surrogate DT - Provides the global feature importance scores (also used by K-LIME clustering) - Used by LOCO to provide an alternative local feature importance to LIME - Used by approximate PDP and ICE plots 23
  • 24. LOCO: Leave One Covariate Out Key idea: feature importance as the difference in model prediction with and without a given feature Approach: approximate prediction without a feature using RF surrogate where contributions of rules involving that feature are removed Pros: - Nonlinear and considers feature interactions => alternative to LIME approximate local explanations Cons: - Difficult to generate a mathematical error rate (unlike LIME) 24
  • 25. ICE: Individual Conditional Expectation How a row prediction varies if ONLY a desired feature varies within its domain? Help explore if the treatment of a specific row is valid in comparison to - Average model behavior (PDP) => discrepancies could reveal possible feature interaction => examine surrogate DT - Known standards - Domain knowledge, and reasonable expectations ICE PDP 25
  • 26. MLI’s global explanations How all (set of) model predictions came about? (what drives model predictions in general) Feature importance Decision logic Prediction behavior when varying a feature Exact Aggregated SHAP NA PDP on DAI model Approximate K-LIME , RF surrogate, Aggregated LOCO? DT surrogate PDP on RF surrogate 26
  • 27. Key idea: response function of a complex model may not be linear globally but it could be piecewise linear Approach: use GLMs to approximate global response of a complex model within local regions (clusters) obtained by: - K-Means applied to the globally most important features provided by RF surrogate model - Decision tree surrogate leafs (LIME-SUP) - An (optional) clustering column provided by customer (based on their domain knowledge) K-LIME 27
  • 28. PDP: Partial Dependence Plot How model predictions vary on average if ONLY a desired feature varies within its domain? Basically aggregate of ICE plots for a given feature Help explore if overall treatment of a specific feature is valid in comparison to - Known standards - Domain knowledge, and reasonable expectations Feature interactions might be averaged out by PDP 28
  • 29. Reason codes A plain English “translation” of K-LIME explanations Three different scopes: global, cluster, and local - Local reason codes come with std dev Also generated for feature contributions provided by SHAP (not shown in UI by downloadable as a CSV) 29
  • 30. MLI’s time series explanations Based on SHAP DAI might split time series data into multiple groups when modelling SHAP explanations are obtained for all forecasts in each group and aggregated up 30
  • 31. Evaluating explanations SHAP explanation should be accurate and consistent, at least in theory Goodness of fit in case of approximate (surrogate) models - R2 and RMSE of training and validation data - Surrogate prediction accuracy - Ranked predictions plot for K-LIME Standard deviation in case of PDP, ICE plots, and reason codes Consistency between different explanation techniques (use MLI dashboard) http://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/interpret-non-ts.html#expectations-for-consistency-between-e xplanatory-techniques 31
  • 32. Assess model’s group fairness through Disparate Impact Analysis (DIA) - For a given feature, e.g. sex, compute average, per group, performance metrics, e.g. accuracy - Compute group disparities as the ratio of group metrics to given reference metric - Flag cases where group disparities are beyond the preset thresholds as biased MLI’s fairness assessment 32
  • 33. Available for binary classification and regression models Could be used for model debugging too, e.g. examine confusion matrix and group metrics of non-protected features Best suited for constrained models (linear, constrained GBM, RuleFit) as the average group metrics reported by DIA is less likely to miss cases of local discrimination MLI’s fairness assessment (cont.) 33
  • 34. Useful MLI resources MLI cheat sheet video by PH (Oct 2018): https://www.youtube.com/watch?v=5jSU3CUReXY MLI Tutorial: https://h2oai.github.io/tutorials/automatic-ml-intro-tutorial/#9 MLI Booklet (May 2019): http://artifacts.h2o.ai.s3.amazonaws.com/releases/ai/h2o/dai/rel-1.6.2-9/docs/booklets/MLIBooklet.pdf 34
  • 36. The what of explainable AI: https://www.elementai.com/news/2019/the-what-of-explainable-ai The why of explainable AI: https://www.elementai.com/news/2019/the-why-of-explainable-ai The how of explainable AI- pre-modelling explainability: https://towardsdatascience.com/the-how-of-explainable-ai-pre-modelling-explainability-699150495fe4 The how of explainable AI- explainable modelling: https://towardsdatascience.com/the-how-of-explainable-ai-explainable-modelling-55c8c43d7bed The how of explainable AI- post-modelling explainability: https://towardsdatascience.com/the-how-of-explainable-ai-post-modelling-explainability-8b4cbc7adf5f Learn more 36