SlideShare une entreprise Scribd logo
1  sur  35
Télécharger pour lire hors ligne
Recent advances in
explainable machine
learning research
Bernease Herman, Research Scientist
University of Washington eScience Institute and
Paul G. Allen School of Computer Science & Engineering
June 6, 2019 - Allen Institute for Artificial Intelligence
Recent advances in
explainable machine
learning research
Bernease Herman, Research Scientist
University of Washington eScience Institute and
Paul G. Allen School of Computer Science & Engineering
June 6, 2019 - Allen Institute for Artificial Intelligence
Speed run edition
eScience Institute
University of Washington
Modified graphic. Original from Alice Zheng
Model
interpretation
Data Curation · Evaluation · Interpretation
Personal research interests in ML
Modified graphic. Original from Alice Zheng
Model
interpretation
Data Curation · Evaluation · Interpretation
How do we choose and collect dataset?
Modified graphic. Original from Alice Zheng
Model
interpretation
Data Curation · Evaluation · Interpretation
How to check performance of ML?
Modified graphic. Original from Alice Zheng
Model
interpretation
Data Curation · Evaluation · Interpretation
What’s happening on the inside?
Interpretable vs Explainable
Defining model explainability
No single definition within community.
“component of interpretable modeling process informing
how model works in understandable form” - Me
“process of giving explanations [of ML] to humans”
- Kim & Doshi-Valez 2017
to left, formal definition (I)
that extends beyond humans
- Dhurandhar et al. 2017
Linear regression models
(with a certain number of parameters)
Decision trees (or similar)
(with a certain depth/number of parameters)
Text explanations
Visualizations (e.g., saliency maps)
more
Explanations come in many forms
“Explanation vehicles” (Herman 2017)
Explanations come in many forms
from “The Mythos of Model Interpretability”, Lipton 2016
1. Simulatability, comprehend the entire model
at once; model complexity
2. Decomposability, comprehend the individual
components/parameters; intelligibility [2]
3. Algorithmic transparency, comprehend
the algorithm behavior; loss surface and randomness
Three levels of transparency
Interpretability methods
(with focus on explanations)
Interpretable methods survey
heavily borrowed from Kim & Doshi-Valez ICML 2017 tutorial
1. Fitting new models that are
intrinsically interpretable
2. Post-hoc analysis of existing model
3. Interpretable analysis of raw data
(or model architecture)
Inherently interpretable models
1. Fitting new models that are
intrinsically interpretable
Decision trees, rule lists, rule sets
Generalized linear models (and feature manipulation)
Case-based methods
Sparsity-based methods
Monotonicity-based methods
Conceptual and hierarchical models
1. Fitting new models that are
intrinsically interpretable.
Decision trees, rule lists, rule sets
Generalized linear models (and feature manipulation)
table above from Gehrke et al. 2012
Inherently interpretable models
figure above from Gupta et al. 2016
Monotonicity constraints
Conceptual and hierarchical models
Inherently interpretable models
2. Post-hoc analysis of existing model
Sensitivity analysis
Surrogate models
Gradient-based methods
Hidden layer investigations
Post-hoc for existing models
2.
Sensitivity analysis
Surrogate models
Patrick Hall et al. 2017, O’Reilly Blog
Post-hoc for existing models
2. Post-hoc analysis of existing model.
Sensitivity analysis
Surrogate models
Gradient-based methods
Surrogate models
Hidden layer investigations
Post-hoc for existing models
figures from Ribeiro et al. 2015 (LIME)
2. Post-hoc analysis of existing mode
Gradient-based methods
Surrogate models
Hidden layer investigations
Post-hoc for existing models
Lundberg & Lee 2017 (SHAP)
2. Post-hoc analysis of existing model
Gradient-based methods
Surrogate models
Hidden layer investigations
Post-hoc for existing models
Lundberg et al. (2019)
2.
Sensitivity analysis
Surrogate models
Gradient-based methods
Selvaraju et al. 2017
Post-hoc for existing models
3. Interpretable analysis of raw data
Visualization
Variable Importance
Partial dependence plots
Correlation analysis
Interpretable raw data analysis
Visualizations for AutoML
Wang et al. (2019)
Do interpretability and
explainability methods
always work?
Explanations can be persuasive
Lipton 2016, Herman 2017
When tailoring our model explanations to
human preferences and judges, our models
may learn to prioritize persuasive
explanations over introspective ones.
Potentially unfaithful explanations
Hendricks et al. 2016
Visual saliency explanation methods
Adebayo et al. 2018
Even random labels don’t stop them
Adebayo et al. 2018
How AI detectives are cracking open the black box of
deep learning, Science Magazine, July 2017
Background reading
Ideas on interpreting machine learning,
O’Reilly Ideas, March 2017
Background reading
Thank you!
Let’s discuss this more.
Bernease Herman
bernease@uw.edu
@bernease on Twitter, Github, MSDSE Slack, everything
Splitting model form from simplicity
Herman 2017
Simultaneously
coerced into suitable
model form
(e.g., decision tree)
and reduced in
complexity
(e.g., model size).
Difficult to evaluate
across complexity
preferences.
Splitting model form from simplicity
Herman 2017
Keeps model form
and reduction of
complexity separate.
Improves evaluation
and adaptability.

Contenu connexe

Tendances

Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Andre Freitas
 
An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!Mansour Saffar
 
20051128.doc
20051128.doc20051128.doc
20051128.docbutest
 
Cmaps as intellectual prosthesis (GERAS 34, Paris)
Cmaps as intellectual prosthesis (GERAS 34, Paris)Cmaps as intellectual prosthesis (GERAS 34, Paris)
Cmaps as intellectual prosthesis (GERAS 34, Paris)Lawrie Hunter
 
A Simple Guide to the Item Response Theory (IRT) and Rasch Modeling
A Simple Guide to the Item Response Theory (IRT) and Rasch ModelingA Simple Guide to the Item Response Theory (IRT) and Rasch Modeling
A Simple Guide to the Item Response Theory (IRT) and Rasch ModelingOpenThink Labs
 
XAI or DIE at Data Science Summit 2019
XAI or DIE at Data Science Summit 2019XAI or DIE at Data Science Summit 2019
XAI or DIE at Data Science Summit 2019Przemek Biecek
 
Ontology based approach for annotating a corpus of computer science abstracts
Ontology based approach for annotating a corpus of computer science abstractsOntology based approach for annotating a corpus of computer science abstracts
Ontology based approach for annotating a corpus of computer science abstractsZainab Almugbel
 
Intro to Discrete Mathematics
Intro to Discrete MathematicsIntro to Discrete Mathematics
Intro to Discrete Mathematicsasad faraz
 
Ontology-based Data Integration
Ontology-based Data IntegrationOntology-based Data Integration
Ontology-based Data IntegrationJanna Hastings
 
Explore, Explain, and Debug aka Interpretable Machine Learning
Explore, Explain, and Debug aka Interpretable Machine LearningExplore, Explain, and Debug aka Interpretable Machine Learning
Explore, Explain, and Debug aka Interpretable Machine LearningPrzemek Biecek
 
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...Sri Ambati
 
A cognitive approach for Modelling and Reasoning on Commonsense Knowledge in...
A cognitive  approach for Modelling and Reasoning on Commonsense Knowledge in...A cognitive  approach for Modelling and Reasoning on Commonsense Knowledge in...
A cognitive approach for Modelling and Reasoning on Commonsense Knowledge in...Antonio Lieto
 
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...Analytics India Magazine
 
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...Sri Ambati
 
Data Integration Ontology Mapping
Data Integration Ontology MappingData Integration Ontology Mapping
Data Integration Ontology MappingPradeep B Pillai
 
Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...
Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...
Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...CSCJournals
 
Intuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years laterIntuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years laterValeria de Paiva
 
Train, explain, acclaim. Build a good model in three steps
Train, explain, acclaim.  Build a good model in three stepsTrain, explain, acclaim.  Build a good model in three steps
Train, explain, acclaim. Build a good model in three stepsPrzemek Biecek
 
How the philosophy of mathematical practice can be logic by other means (bris...
How the philosophy of mathematical practice can be logic by other means (bris...How the philosophy of mathematical practice can be logic by other means (bris...
How the philosophy of mathematical practice can be logic by other means (bris...Brendan Larvor
 
Report
ReportReport
Reportbutest
 

Tendances (20)

Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...
 
An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!An Introduction to XAI! Towards Trusting Your ML Models!
An Introduction to XAI! Towards Trusting Your ML Models!
 
20051128.doc
20051128.doc20051128.doc
20051128.doc
 
Cmaps as intellectual prosthesis (GERAS 34, Paris)
Cmaps as intellectual prosthesis (GERAS 34, Paris)Cmaps as intellectual prosthesis (GERAS 34, Paris)
Cmaps as intellectual prosthesis (GERAS 34, Paris)
 
A Simple Guide to the Item Response Theory (IRT) and Rasch Modeling
A Simple Guide to the Item Response Theory (IRT) and Rasch ModelingA Simple Guide to the Item Response Theory (IRT) and Rasch Modeling
A Simple Guide to the Item Response Theory (IRT) and Rasch Modeling
 
XAI or DIE at Data Science Summit 2019
XAI or DIE at Data Science Summit 2019XAI or DIE at Data Science Summit 2019
XAI or DIE at Data Science Summit 2019
 
Ontology based approach for annotating a corpus of computer science abstracts
Ontology based approach for annotating a corpus of computer science abstractsOntology based approach for annotating a corpus of computer science abstracts
Ontology based approach for annotating a corpus of computer science abstracts
 
Intro to Discrete Mathematics
Intro to Discrete MathematicsIntro to Discrete Mathematics
Intro to Discrete Mathematics
 
Ontology-based Data Integration
Ontology-based Data IntegrationOntology-based Data Integration
Ontology-based Data Integration
 
Explore, Explain, and Debug aka Interpretable Machine Learning
Explore, Explain, and Debug aka Interpretable Machine LearningExplore, Explain, and Debug aka Interpretable Machine Learning
Explore, Explain, and Debug aka Interpretable Machine Learning
 
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
 
A cognitive approach for Modelling and Reasoning on Commonsense Knowledge in...
A cognitive  approach for Modelling and Reasoning on Commonsense Knowledge in...A cognitive  approach for Modelling and Reasoning on Commonsense Knowledge in...
A cognitive approach for Modelling and Reasoning on Commonsense Knowledge in...
 
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...
 
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
 
Data Integration Ontology Mapping
Data Integration Ontology MappingData Integration Ontology Mapping
Data Integration Ontology Mapping
 
Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...
Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...
Automated Education Propositional Logic Tool (AEPLT): Used For Computation in...
 
Intuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years laterIntuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years later
 
Train, explain, acclaim. Build a good model in three steps
Train, explain, acclaim.  Build a good model in three stepsTrain, explain, acclaim.  Build a good model in three steps
Train, explain, acclaim. Build a good model in three steps
 
How the philosophy of mathematical practice can be logic by other means (bris...
How the philosophy of mathematical practice can be logic by other means (bris...How the philosophy of mathematical practice can be logic by other means (bris...
How the philosophy of mathematical practice can be logic by other means (bris...
 
Report
ReportReport
Report
 

Similaire à Rsqrd AI: Recent Advances in Explainable Machine Learning Research

Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"Aalto University
 
​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!Eindhoven University of Technology / JADS
 
Statistical Modeling in 3D: Describing, Explaining and Predicting
Statistical Modeling in 3D: Describing, Explaining and PredictingStatistical Modeling in 3D: Describing, Explaining and Predicting
Statistical Modeling in 3D: Describing, Explaining and PredictingGalit Shmueli
 
Statistical Modeling in 3D: Explaining, Predicting, Describing
Statistical Modeling in 3D: Explaining, Predicting, DescribingStatistical Modeling in 3D: Explaining, Predicting, Describing
Statistical Modeling in 3D: Explaining, Predicting, DescribingGalit Shmueli
 
To Explain, To Predict, or To Describe?
To Explain, To Predict, or To Describe?To Explain, To Predict, or To Describe?
To Explain, To Predict, or To Describe?Galit Shmueli
 
ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...
ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...
ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...Mahmoud Elbattah
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...kellynguyen01
 
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and AbstractIEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and Abstracttsysglobalsolutions
 
Probabilistic Topic Models
Probabilistic Topic ModelsProbabilistic Topic Models
Probabilistic Topic ModelsSteve Follmer
 
The effect of number of concepts on readability of schemas 2
The effect of number of concepts on readability of schemas 2The effect of number of concepts on readability of schemas 2
The effect of number of concepts on readability of schemas 2Saman Sara
 
Tips for Scale Development: Evaluating Automatic Personas
Tips for Scale Development: Evaluating Automatic PersonasTips for Scale Development: Evaluating Automatic Personas
Tips for Scale Development: Evaluating Automatic PersonasJoni Salminen
 
Interpretable Machine Learning
Interpretable Machine LearningInterpretable Machine Learning
Interpretable Machine LearningSri Ambati
 
Big Data - To Explain or To Predict? Talk at U Toronto's Rotman School of Ma...
Big Data - To Explain or To Predict?  Talk at U Toronto's Rotman School of Ma...Big Data - To Explain or To Predict?  Talk at U Toronto's Rotman School of Ma...
Big Data - To Explain or To Predict? Talk at U Toronto's Rotman School of Ma...Galit Shmueli
 
Evolving Swings (topics) from Social Streams using Probability Model
Evolving Swings (topics) from Social Streams using Probability ModelEvolving Swings (topics) from Social Streams using Probability Model
Evolving Swings (topics) from Social Streams using Probability ModelIJERA Editor
 
Keepler Data Tech | Entendiendo tus propios modelos predictivos
Keepler Data Tech | Entendiendo tus propios modelos predictivosKeepler Data Tech | Entendiendo tus propios modelos predictivos
Keepler Data Tech | Entendiendo tus propios modelos predictivosKeepler Data Tech
 
NE7012- SOCIAL NETWORK ANALYSIS
NE7012- SOCIAL NETWORK ANALYSISNE7012- SOCIAL NETWORK ANALYSIS
NE7012- SOCIAL NETWORK ANALYSISrathnaarul
 
A Categorisation of Post-hoc Explanations for Predictive Models
A Categorisation of Post-hoc Explanations for Predictive ModelsA Categorisation of Post-hoc Explanations for Predictive Models
A Categorisation of Post-hoc Explanations for Predictive ModelsJane Dane
 
Recommenders, Topics, and Text
Recommenders, Topics, and TextRecommenders, Topics, and Text
Recommenders, Topics, and TextNBER
 
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for EveryoneGDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for EveryoneJames Anderson
 

Similaire à Rsqrd AI: Recent Advances in Explainable Machine Learning Research (20)

Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"
 
​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!​​Explainability in AI and Recommender systems: let’s make it interactive!
​​Explainability in AI and Recommender systems: let’s make it interactive!
 
Statistical Modeling in 3D: Describing, Explaining and Predicting
Statistical Modeling in 3D: Describing, Explaining and PredictingStatistical Modeling in 3D: Describing, Explaining and Predicting
Statistical Modeling in 3D: Describing, Explaining and Predicting
 
Statistical Modeling in 3D: Explaining, Predicting, Describing
Statistical Modeling in 3D: Explaining, Predicting, DescribingStatistical Modeling in 3D: Explaining, Predicting, Describing
Statistical Modeling in 3D: Explaining, Predicting, Describing
 
To Explain, To Predict, or To Describe?
To Explain, To Predict, or To Describe?To Explain, To Predict, or To Describe?
To Explain, To Predict, or To Describe?
 
ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...
ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...
ML-Aided Simulation: A Conceptual Framework for Integrating Simulation Models...
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
 
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and AbstractIEEE Pattern analysis and machine intelligence 2016 Title and Abstract
IEEE Pattern analysis and machine intelligence 2016 Title and Abstract
 
Probabilistic Topic Models
Probabilistic Topic ModelsProbabilistic Topic Models
Probabilistic Topic Models
 
The effect of number of concepts on readability of schemas 2
The effect of number of concepts on readability of schemas 2The effect of number of concepts on readability of schemas 2
The effect of number of concepts on readability of schemas 2
 
1808.10245v1 (1).pdf
1808.10245v1 (1).pdf1808.10245v1 (1).pdf
1808.10245v1 (1).pdf
 
Tips for Scale Development: Evaluating Automatic Personas
Tips for Scale Development: Evaluating Automatic PersonasTips for Scale Development: Evaluating Automatic Personas
Tips for Scale Development: Evaluating Automatic Personas
 
Interpretable Machine Learning
Interpretable Machine LearningInterpretable Machine Learning
Interpretable Machine Learning
 
Big Data - To Explain or To Predict? Talk at U Toronto's Rotman School of Ma...
Big Data - To Explain or To Predict?  Talk at U Toronto's Rotman School of Ma...Big Data - To Explain or To Predict?  Talk at U Toronto's Rotman School of Ma...
Big Data - To Explain or To Predict? Talk at U Toronto's Rotman School of Ma...
 
Evolving Swings (topics) from Social Streams using Probability Model
Evolving Swings (topics) from Social Streams using Probability ModelEvolving Swings (topics) from Social Streams using Probability Model
Evolving Swings (topics) from Social Streams using Probability Model
 
Keepler Data Tech | Entendiendo tus propios modelos predictivos
Keepler Data Tech | Entendiendo tus propios modelos predictivosKeepler Data Tech | Entendiendo tus propios modelos predictivos
Keepler Data Tech | Entendiendo tus propios modelos predictivos
 
NE7012- SOCIAL NETWORK ANALYSIS
NE7012- SOCIAL NETWORK ANALYSISNE7012- SOCIAL NETWORK ANALYSIS
NE7012- SOCIAL NETWORK ANALYSIS
 
A Categorisation of Post-hoc Explanations for Predictive Models
A Categorisation of Post-hoc Explanations for Predictive ModelsA Categorisation of Post-hoc Explanations for Predictive Models
A Categorisation of Post-hoc Explanations for Predictive Models
 
Recommenders, Topics, and Text
Recommenders, Topics, and TextRecommenders, Topics, and Text
Recommenders, Topics, and Text
 
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for EveryoneGDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
GDG Cloud Southlake #17: Meg Dickey-Kurdziolek: Explainable AI is for Everyone
 

Plus de Sanjana Chowdhury

Rsqrd AI: Making Conversational AI Work for Everybody
Rsqrd AI: Making Conversational AI Work for EverybodyRsqrd AI: Making Conversational AI Work for Everybody
Rsqrd AI: Making Conversational AI Work for EverybodySanjana Chowdhury
 
Rsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in HealthcareRsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in HealthcareSanjana Chowdhury
 
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text ClassificationRsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text ClassificationSanjana Chowdhury
 
Rsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial PerturbationsRsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial PerturbationsSanjana Chowdhury
 
Rsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability TechniquesRsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability TechniquesSanjana Chowdhury
 
Rsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric IntuitionRsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric IntuitionSanjana Chowdhury
 
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error AnalysisRsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error AnalysisSanjana Chowdhury
 
Rsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model PredictionsRsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model PredictionsSanjana Chowdhury
 
Rsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI PlatformRsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI PlatformSanjana Chowdhury
 
Rsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first StartupRsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first StartupSanjana Chowdhury
 
Rsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AIRsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AISanjana Chowdhury
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineSanjana Chowdhury
 

Plus de Sanjana Chowdhury (12)

Rsqrd AI: Making Conversational AI Work for Everybody
Rsqrd AI: Making Conversational AI Work for EverybodyRsqrd AI: Making Conversational AI Work for Everybody
Rsqrd AI: Making Conversational AI Work for Everybody
 
Rsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in HealthcareRsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in Healthcare
 
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text ClassificationRsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
 
Rsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial PerturbationsRsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
 
Rsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability TechniquesRsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
 
Rsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric IntuitionRsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric Intuition
 
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error AnalysisRsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
 
Rsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model PredictionsRsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model Predictions
 
Rsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI PlatformRsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI Platform
 
Rsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first StartupRsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first Startup
 
Rsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AIRsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AI
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
 

Dernier

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Bhuvaneswari Subramani
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamUiPathCommunity
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxRemote DBA Services
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelDeepika Singh
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 

Dernier (20)

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 

Rsqrd AI: Recent Advances in Explainable Machine Learning Research

  • 1. Recent advances in explainable machine learning research Bernease Herman, Research Scientist University of Washington eScience Institute and Paul G. Allen School of Computer Science & Engineering June 6, 2019 - Allen Institute for Artificial Intelligence
  • 2. Recent advances in explainable machine learning research Bernease Herman, Research Scientist University of Washington eScience Institute and Paul G. Allen School of Computer Science & Engineering June 6, 2019 - Allen Institute for Artificial Intelligence Speed run edition
  • 4. Modified graphic. Original from Alice Zheng Model interpretation Data Curation · Evaluation · Interpretation Personal research interests in ML
  • 5. Modified graphic. Original from Alice Zheng Model interpretation Data Curation · Evaluation · Interpretation How do we choose and collect dataset?
  • 6. Modified graphic. Original from Alice Zheng Model interpretation Data Curation · Evaluation · Interpretation How to check performance of ML?
  • 7. Modified graphic. Original from Alice Zheng Model interpretation Data Curation · Evaluation · Interpretation What’s happening on the inside?
  • 9. Defining model explainability No single definition within community. “component of interpretable modeling process informing how model works in understandable form” - Me “process of giving explanations [of ML] to humans” - Kim & Doshi-Valez 2017 to left, formal definition (I) that extends beyond humans - Dhurandhar et al. 2017
  • 10. Linear regression models (with a certain number of parameters) Decision trees (or similar) (with a certain depth/number of parameters) Text explanations Visualizations (e.g., saliency maps) more Explanations come in many forms
  • 11. “Explanation vehicles” (Herman 2017) Explanations come in many forms
  • 12. from “The Mythos of Model Interpretability”, Lipton 2016 1. Simulatability, comprehend the entire model at once; model complexity 2. Decomposability, comprehend the individual components/parameters; intelligibility [2] 3. Algorithmic transparency, comprehend the algorithm behavior; loss surface and randomness Three levels of transparency
  • 14. Interpretable methods survey heavily borrowed from Kim & Doshi-Valez ICML 2017 tutorial 1. Fitting new models that are intrinsically interpretable 2. Post-hoc analysis of existing model 3. Interpretable analysis of raw data (or model architecture)
  • 15. Inherently interpretable models 1. Fitting new models that are intrinsically interpretable Decision trees, rule lists, rule sets Generalized linear models (and feature manipulation) Case-based methods Sparsity-based methods Monotonicity-based methods Conceptual and hierarchical models
  • 16. 1. Fitting new models that are intrinsically interpretable. Decision trees, rule lists, rule sets Generalized linear models (and feature manipulation) table above from Gehrke et al. 2012 Inherently interpretable models
  • 17. figure above from Gupta et al. 2016 Monotonicity constraints Conceptual and hierarchical models Inherently interpretable models
  • 18. 2. Post-hoc analysis of existing model Sensitivity analysis Surrogate models Gradient-based methods Hidden layer investigations Post-hoc for existing models
  • 19. 2. Sensitivity analysis Surrogate models Patrick Hall et al. 2017, O’Reilly Blog Post-hoc for existing models
  • 20. 2. Post-hoc analysis of existing model. Sensitivity analysis Surrogate models Gradient-based methods Surrogate models Hidden layer investigations Post-hoc for existing models figures from Ribeiro et al. 2015 (LIME)
  • 21. 2. Post-hoc analysis of existing mode Gradient-based methods Surrogate models Hidden layer investigations Post-hoc for existing models Lundberg & Lee 2017 (SHAP)
  • 22. 2. Post-hoc analysis of existing model Gradient-based methods Surrogate models Hidden layer investigations Post-hoc for existing models Lundberg et al. (2019)
  • 23. 2. Sensitivity analysis Surrogate models Gradient-based methods Selvaraju et al. 2017 Post-hoc for existing models
  • 24. 3. Interpretable analysis of raw data Visualization Variable Importance Partial dependence plots Correlation analysis Interpretable raw data analysis
  • 27. Explanations can be persuasive Lipton 2016, Herman 2017 When tailoring our model explanations to human preferences and judges, our models may learn to prioritize persuasive explanations over introspective ones.
  • 29. Visual saliency explanation methods Adebayo et al. 2018
  • 30. Even random labels don’t stop them Adebayo et al. 2018
  • 31. How AI detectives are cracking open the black box of deep learning, Science Magazine, July 2017 Background reading
  • 32. Ideas on interpreting machine learning, O’Reilly Ideas, March 2017 Background reading
  • 33. Thank you! Let’s discuss this more. Bernease Herman bernease@uw.edu @bernease on Twitter, Github, MSDSE Slack, everything
  • 34. Splitting model form from simplicity Herman 2017 Simultaneously coerced into suitable model form (e.g., decision tree) and reduced in complexity (e.g., model size). Difficult to evaluate across complexity preferences.
  • 35. Splitting model form from simplicity Herman 2017 Keeps model form and reduction of complexity separate. Improves evaluation and adaptability.