SlideShare a Scribd company logo
1 of 34
Download to read offline
2
● Applied Mathematics, Data Science
● SW Engineering, Machine Learning
● Big Data, Hadoop, Spark
mspitzer@inovex.de
@mspitzer243
3
Interpretation
is the process of
giving explanations
to humans.
~ B. Kim, Google Brain, Interpretable
Machine Learning (ICML 2017)
https://people.csail.mit.edu/beenkim/papers/BeenK_FinaleDV_ICML2017_tutorial.pdf
4
“Interpretability is the degree to which an observer
can understand the cause of a decision.”
~ Miller T., 2017, Explanation in AI: Insights from the Social Sciences
● humans create decision systems
● humans are affected by decisions
● humans demand for explanations
https://arxiv.org/pdf/1706.07269.pdf
5
Bias towards Accuracy
Do also consider asking yourself:
● Am I solving the right problem?
● How to make people trust my algorithm?
● Is there any bias? Are the training data representative?
● What is the impact in a real-world setting?
https://bentoml.com/posts/2019-04-19-one-model/
“The machine learning community focuses too much on predictive performance.
But machine learning models are always a small part of a complex system.”
~ C. Molnar, 2019, One Model to Rule Them All
6https://arxiv.org/abs/1602.04938
7https://arxiv.org/pdf/1606.03490.pdf
The additional need for interpretability
8https://arxiv.org/pdf/1606.03490.pdf
The additional need for interpretability
The decision process of a model
should be consistent to the
domain knowledge of an expert.
In particular, it ...
● should not encode bias
● should not pick up random correlation
● should not use leaked information
hard to capture in asingle quantity
9
Use models that are intrinsically interpretable and
known to be easy for humans to understand.
Train a black box model and apply post-hoc
interpretability techniques to provide explanations.
1
2
10
Linear Regression
Linearity makes model easy to interpret
● learned weights can be used to explain feature effects
● predictions can be decomposed into individual attributions
● confidence intervals express uncertainty
Linear Regression: Model Internals
https://christophm.github.io/interpretable-ml-book/limo.html
● Coefficients indicate direction
of influence
● Confidence intervals express
significance and uncertainty
● Not comparable across
features unless standardized
Linear Regression: Feature Effects
https://christophm.github.io/interpretable-ml-book/limo.html
● Decompose predictions into
individual feature attributions
● Scale-independent, hence
comparable across features
● Enables us to draw conclusions
about feature importance
https://christophm.github.io/interpretable-ml-book/limo.html
Linear Regression: Feature Effects
● Decompose predictions into
individual feature attributions
● Scale-independent, hence
comparable across features
● Enables us to draw conclusions
about feature importance
● Individual effects comparable
to overall distribution
14
Decision Trees
Intuitive decision process makes model easy to interpret
● captures nonlinear dependencies and interactions
● model is simple and self-describing
● rule-based prediction feels natural for humans
15
Decision Trees: Model Internals
income > X?
dept < Y?
YESNO
NO
has larger
impact than
dept
● Tree structure lets us assess
feature importance
16
Decision Trees: Model Internals
income > X?
dept < Y?
YESNO
NO
● Tree structure lets us assess
feature importance
● Feature interactions can be
determined by following paths
from root to leaf
17
Decision Trees: Individual Explanations
income > X?
dept < Y?
YESNO
NO
● Tree structure lets us assess
feature importance
● Feature interactions can be
determined by following paths
from root to leaf
● To explain a particular
prediction, just take a look at
the path from root to leaf
18
Wrap Up: Desirable Properties
Intrinsically interpretable models simplify answering:
● Which features are relevant?
● How do they influence predictions?
● How do features interact?
● How certain is a prediction?
Both for the entire model as well as individual predictions
19
Wrap Up: Desirable Properties
Intrinsically interpretable models simplify answering:
● Which features are relevant?
● How do they influence predictions?
● How do features interact?
● How certain is a prediction?
Both for the entire model as well as individual predictions
How to answer these questions
if models were black boxes?
20
Use models that are intrinsically interpretable and
known to be easy for humans to understand.
Train a black box model and apply post-hoc
interpretability techniques to provide explanations.
1
2
21
Feature Shuffling
https://amunategui.github.io/variable-importance-shuffler/
Train Model Apply
Shuffle
Evaluate
Training
Testing Shuffled
Scored
RMSE’=4.8
Evaluate
Scored
RMSE=3.2
X
X’
For every Feature X:
Repeat this process N times
X’
= Perm(X)
Degradation(RMSE,X) = 4.8 - 3.2 = 1.6
22
Feature Shuffling
https://christophm.github.io/interpretable-ml-book/feature-importance.html https://scikit-plot.readthedocs.io/en/stable/estimators.html#scikitplot.estimators.plot_feature_importances
● Estimates Feature importance
by averaging degradation
● Tied to certain loss function
● Not applicable in high
dimensional domains
23
Individual Conditional Expectation (ICE)
https://christophm.github.io/interpretable-ml-book/pdp.html
Train Model
Training
Testing
Overwrite
Modified
X
Apply
Scored
X’
X’ = Const
XFor every Feature X:
Repeat this process using some constants CX
ŷ
24
Individual Conditional Expectation (ICE)
https://christophm.github.io/interpretable-ml-book/pdp.html
25
Individual Conditional Expectation (ICE)
https://christophm.github.io/interpretable-ml-book/pdp.html
26
Individual Conditional Expectation (ICE)
https://christophm.github.io/interpretable-ml-book/pdp.html
27
Global Surrogate Models
https://www.oreilly.com/ideas/ideas-on-interpreting-machine-learning
● Feeds original model with small
variations of instance to be explained
● Sampled instances are weighted by
proximity to the instance of interest
● Interpretable models are fit locally
on observed outcome
28
Local Surrogate Models (LIME)
https://christophm.github.io/interpretable-ml-book/lime.html
29
Local Surrogate Models (LIME)
https://www.oreilly.com/learning/introduction-to-local-interpretable-model-agnostic-explanations-lime
30
Conclusion
● performance metrics are crucial for evaluation,
but they lack explanations
● criteria like fairness and consistency are much
harder if not impossible to quantify
● the problem with blackboxes is the lack of trust
caused by their opaque nature
● transparency is key to achieving trust and
acceptance in the mainstream
31https://xkcd.com/1838/
Conclusion
don’t end up like this!
● Molnar C., 2018, Interpretable Machine Learning - A Guide for Making
Black Box Models Explainable
● Gill N., Hall P., 2018, An Introduction to Machine Learning Interpretability
● Zhao Q., Hastie T., 2017, Causal Interpretations of Black-Box Models
● Kim B., Doshi-Velez F., 2017, Interpretable Machine Learning: The fuss, the
concrete and the questions
● Ribeiro, M.T., Singh, S. and Guestrin, C., 2016, August. Why should i trust
you? Explaining the predictions of any classifier
32
Resources
33
Marcel Spitzer
Big Data Scientist
mspitzer@inovex.de
inovex GmbH
Schanzenstraße 6-20
Kupferhütte 1.13
51063 Köln

More Related Content

What's hot

Explainability and bias in AI
Explainability and bias in AIExplainability and bias in AI
Explainability and bias in AIBill Liu
 
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
 
Interpretable machine learning
Interpretable machine learningInterpretable machine learning
Interpretable machine learningSri Ambati
 
Explainable AI (XAI) - A Perspective
Explainable AI (XAI) - A Perspective Explainable AI (XAI) - A Perspective
Explainable AI (XAI) - A Perspective Saurabh Kaushik
 
Towards Human-Centered Machine Learning
Towards Human-Centered Machine LearningTowards Human-Centered Machine Learning
Towards Human-Centered Machine LearningSri Ambati
 
Explainable AI: Building trustworthy AI models?
Explainable AI: Building trustworthy AI models? Explainable AI: Building trustworthy AI models?
Explainable AI: Building trustworthy AI models? Raheel Ahmad
 
Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Krishnaram Kenthapadi
 
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
 
The Evolution of AutoML
The Evolution of AutoMLThe Evolution of AutoML
The Evolution of AutoMLNing Jiang
 
Interpretability of machine learning
Interpretability of machine learningInterpretability of machine learning
Interpretability of machine learningDaiki Tanaka
 
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...Sri Ambati
 
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
 
How to fine-tune and develop your own large language model.pptx
How to fine-tune and develop your own large language model.pptxHow to fine-tune and develop your own large language model.pptx
How to fine-tune and develop your own large language model.pptxKnoldus Inc.
 
Automatic Machine Learning, AutoML
Automatic Machine Learning, AutoMLAutomatic Machine Learning, AutoML
Automatic Machine Learning, AutoMLHimadri Mishra
 
Explainable AI
Explainable AIExplainable AI
Explainable AIDinesh V
 
A Unified Approach to Interpreting Model Predictions (SHAP)
A Unified Approach to Interpreting Model Predictions (SHAP)A Unified Approach to Interpreting Model Predictions (SHAP)
A Unified Approach to Interpreting Model Predictions (SHAP)Rama Irsheidat
 
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
 

What's hot (20)

Explainable AI
Explainable AIExplainable AI
Explainable AI
 
Explainability and bias in AI
Explainability and bias in AIExplainability and bias in AI
Explainability and bias in AI
 
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!
 
Interpretable machine learning
Interpretable machine learningInterpretable machine learning
Interpretable machine learning
 
Explainable AI (XAI) - A Perspective
Explainable AI (XAI) - A Perspective Explainable AI (XAI) - A Perspective
Explainable AI (XAI) - A Perspective
 
Towards Human-Centered Machine Learning
Towards Human-Centered Machine LearningTowards Human-Centered Machine Learning
Towards Human-Centered Machine Learning
 
Explainable AI: Building trustworthy AI models?
Explainable AI: Building trustworthy AI models? Explainable AI: Building trustworthy AI models?
Explainable AI: Building trustworthy AI models?
 
Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)
 
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
 
The Evolution of AutoML
The Evolution of AutoMLThe Evolution of AutoML
The Evolution of AutoML
 
eScience SHAP talk
eScience SHAP talkeScience SHAP talk
eScience SHAP talk
 
Shap
ShapShap
Shap
 
Interpretability of machine learning
Interpretability of machine learningInterpretability of machine learning
Interpretability of machine learning
 
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...
 
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)
 
How to fine-tune and develop your own large language model.pptx
How to fine-tune and develop your own large language model.pptxHow to fine-tune and develop your own large language model.pptx
How to fine-tune and develop your own large language model.pptx
 
Automatic Machine Learning, AutoML
Automatic Machine Learning, AutoMLAutomatic Machine Learning, AutoML
Automatic Machine Learning, AutoML
 
Explainable AI
Explainable AIExplainable AI
Explainable AI
 
A Unified Approach to Interpreting Model Predictions (SHAP)
A Unified Approach to Interpreting Model Predictions (SHAP)A Unified Approach to Interpreting Model Predictions (SHAP)
A Unified Approach to Interpreting Model Predictions (SHAP)
 
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!
 

Similar to Interpretable Machine Learning

Machine Learning Interpretability
Machine Learning InterpretabilityMachine Learning Interpretability
Machine Learning Interpretabilityinovex GmbH
 
Human in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIHuman in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIPramit Choudhary
 
Learning to Learn Model Behavior ( Capital One: data intelligence conference )
Learning to Learn Model Behavior ( Capital One: data intelligence conference )Learning to Learn Model Behavior ( Capital One: data intelligence conference )
Learning to Learn Model Behavior ( Capital One: data intelligence conference )Pramit Choudhary
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learningPramit Choudhary
 
Keynote at-icpc-2020
Keynote at-icpc-2020Keynote at-icpc-2020
Keynote at-icpc-2020Ralf Laemmel
 
The abstract art of software development
The abstract art of software developmentThe abstract art of software development
The abstract art of software developmentStephen Erdman
 
Humane assessment on cards
Humane assessment on cardsHumane assessment on cards
Humane assessment on cardsTudor Girba
 
​​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
 
The importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systemsThe importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systemsFrancesca Lazzeri, PhD
 
BSSML16 L5. Summary Day 1 Sessions
BSSML16 L5. Summary Day 1 SessionsBSSML16 L5. Summary Day 1 Sessions
BSSML16 L5. Summary Day 1 SessionsBigML, Inc
 
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15MLconf
 
10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConf10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConfXavier Amatriain
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systemsXavier Amatriain
 
Model Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep LearningModel Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep LearningPramit Choudhary
 
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning SystemsXavier Amatriain
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Xavier Amatriain
 
NYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell Rebo
NYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell ReboNYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell Rebo
NYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell ReboMaryam Farooq
 

Similar to Interpretable Machine Learning (20)

Learning to learn Model Behavior: How to use "human-in-the-loop" to explain d...
Learning to learn Model Behavior: How to use "human-in-the-loop" to explain d...Learning to learn Model Behavior: How to use "human-in-the-loop" to explain d...
Learning to learn Model Behavior: How to use "human-in-the-loop" to explain d...
 
Machine Learning Interpretability
Machine Learning InterpretabilityMachine Learning Interpretability
Machine Learning Interpretability
 
C3 w5
C3 w5C3 w5
C3 w5
 
Human in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIHuman in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AI
 
Learning to Learn Model Behavior ( Capital One: data intelligence conference )
Learning to Learn Model Behavior ( Capital One: data intelligence conference )Learning to Learn Model Behavior ( Capital One: data intelligence conference )
Learning to Learn Model Behavior ( Capital One: data intelligence conference )
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learning
 
Keynote at-icpc-2020
Keynote at-icpc-2020Keynote at-icpc-2020
Keynote at-icpc-2020
 
The abstract art of software development
The abstract art of software developmentThe abstract art of software development
The abstract art of software development
 
Humane assessment on cards
Humane assessment on cardsHumane assessment on cards
Humane assessment on cards
 
​​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!
 
The importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systemsThe importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systems
 
BSSML16 L5. Summary Day 1 Sessions
BSSML16 L5. Summary Day 1 SessionsBSSML16 L5. Summary Day 1 Sessions
BSSML16 L5. Summary Day 1 Sessions
 
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
 
10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConf10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConf
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems
 
Model Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep LearningModel Evaluation in the land of Deep Learning
Model Evaluation in the land of Deep Learning
 
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
 
NYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell Rebo
NYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell ReboNYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell Rebo
NYAI #25: Evolution Strategies: An Alternative Approach to AI w/ Maxwell Rebo
 

More from inovex GmbH

lldb – Debugger auf Abwegen
lldb – Debugger auf Abwegenlldb – Debugger auf Abwegen
lldb – Debugger auf Abwegeninovex GmbH
 
Are you sure about that?! Uncertainty Quantification in AI
Are you sure about that?! Uncertainty Quantification in AIAre you sure about that?! Uncertainty Quantification in AI
Are you sure about that?! Uncertainty Quantification in AIinovex GmbH
 
Why natural language is next step in the AI evolution
Why natural language is next step in the AI evolutionWhy natural language is next step in the AI evolution
Why natural language is next step in the AI evolutioninovex GmbH
 
Network Policies
Network PoliciesNetwork Policies
Network Policiesinovex GmbH
 
Jenkins X – CI/CD in wolkigen Umgebungen
Jenkins X – CI/CD in wolkigen UmgebungenJenkins X – CI/CD in wolkigen Umgebungen
Jenkins X – CI/CD in wolkigen Umgebungeninovex GmbH
 
AI auf Edge-Geraeten
AI auf Edge-GeraetenAI auf Edge-Geraeten
AI auf Edge-Geraeteninovex GmbH
 
Prometheus on Kubernetes
Prometheus on KubernetesPrometheus on Kubernetes
Prometheus on Kubernetesinovex GmbH
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender Systemsinovex GmbH
 
Representation Learning von Zeitreihen
Representation Learning von ZeitreihenRepresentation Learning von Zeitreihen
Representation Learning von Zeitreiheninovex GmbH
 
Talk to me – Chatbots und digitale Assistenten
Talk to me – Chatbots und digitale AssistentenTalk to me – Chatbots und digitale Assistenten
Talk to me – Chatbots und digitale Assistenteninovex GmbH
 
Künstlich intelligent?
Künstlich intelligent?Künstlich intelligent?
Künstlich intelligent?inovex GmbH
 
Das Android Open Source Project
Das Android Open Source ProjectDas Android Open Source Project
Das Android Open Source Projectinovex GmbH
 
Performance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use casePerformance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use caseinovex GmbH
 
People & Products – Lessons learned from the daily IT madness
People & Products – Lessons learned from the daily IT madnessPeople & Products – Lessons learned from the daily IT madness
People & Products – Lessons learned from the daily IT madnessinovex GmbH
 
Infrastructure as (real) Code – Manage your K8s resources with Pulumi
Infrastructure as (real) Code – Manage your K8s resources with PulumiInfrastructure as (real) Code – Manage your K8s resources with Pulumi
Infrastructure as (real) Code – Manage your K8s resources with Pulumiinovex GmbH
 
Remote First – Der Arbeitsplatz in der Cloud
Remote First – Der Arbeitsplatz in der CloudRemote First – Der Arbeitsplatz in der Cloud
Remote First – Der Arbeitsplatz in der Cloudinovex GmbH
 
Data Science und Machine Learning im Kubernetes-Ökosystem
Data Science und Machine Learning im Kubernetes-ÖkosystemData Science und Machine Learning im Kubernetes-Ökosystem
Data Science und Machine Learning im Kubernetes-Ökosysteminovex GmbH
 

More from inovex GmbH (20)

lldb – Debugger auf Abwegen
lldb – Debugger auf Abwegenlldb – Debugger auf Abwegen
lldb – Debugger auf Abwegen
 
Are you sure about that?! Uncertainty Quantification in AI
Are you sure about that?! Uncertainty Quantification in AIAre you sure about that?! Uncertainty Quantification in AI
Are you sure about that?! Uncertainty Quantification in AI
 
Why natural language is next step in the AI evolution
Why natural language is next step in the AI evolutionWhy natural language is next step in the AI evolution
Why natural language is next step in the AI evolution
 
WWDC 2019 Recap
WWDC 2019 RecapWWDC 2019 Recap
WWDC 2019 Recap
 
Network Policies
Network PoliciesNetwork Policies
Network Policies
 
Jenkins X – CI/CD in wolkigen Umgebungen
Jenkins X – CI/CD in wolkigen UmgebungenJenkins X – CI/CD in wolkigen Umgebungen
Jenkins X – CI/CD in wolkigen Umgebungen
 
AI auf Edge-Geraeten
AI auf Edge-GeraetenAI auf Edge-Geraeten
AI auf Edge-Geraeten
 
Prometheus on Kubernetes
Prometheus on KubernetesPrometheus on Kubernetes
Prometheus on Kubernetes
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender Systems
 
Azure IoT Edge
Azure IoT EdgeAzure IoT Edge
Azure IoT Edge
 
Representation Learning von Zeitreihen
Representation Learning von ZeitreihenRepresentation Learning von Zeitreihen
Representation Learning von Zeitreihen
 
Talk to me – Chatbots und digitale Assistenten
Talk to me – Chatbots und digitale AssistentenTalk to me – Chatbots und digitale Assistenten
Talk to me – Chatbots und digitale Assistenten
 
Künstlich intelligent?
Künstlich intelligent?Künstlich intelligent?
Künstlich intelligent?
 
Dev + Ops = Go
Dev + Ops = GoDev + Ops = Go
Dev + Ops = Go
 
Das Android Open Source Project
Das Android Open Source ProjectDas Android Open Source Project
Das Android Open Source Project
 
Performance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use casePerformance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use case
 
People & Products – Lessons learned from the daily IT madness
People & Products – Lessons learned from the daily IT madnessPeople & Products – Lessons learned from the daily IT madness
People & Products – Lessons learned from the daily IT madness
 
Infrastructure as (real) Code – Manage your K8s resources with Pulumi
Infrastructure as (real) Code – Manage your K8s resources with PulumiInfrastructure as (real) Code – Manage your K8s resources with Pulumi
Infrastructure as (real) Code – Manage your K8s resources with Pulumi
 
Remote First – Der Arbeitsplatz in der Cloud
Remote First – Der Arbeitsplatz in der CloudRemote First – Der Arbeitsplatz in der Cloud
Remote First – Der Arbeitsplatz in der Cloud
 
Data Science und Machine Learning im Kubernetes-Ökosystem
Data Science und Machine Learning im Kubernetes-ÖkosystemData Science und Machine Learning im Kubernetes-Ökosystem
Data Science und Machine Learning im Kubernetes-Ökosystem
 

Recently uploaded

Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...SelfMade bd
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2
 
tonesoftg
tonesoftgtonesoftg
tonesoftglanshi9
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnAmarnathKambale
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in sowetomasabamasaba
 
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...Bert Jan Schrijver
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...Shane Coughlan
 
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open SourceWSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open SourceWSO2
 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...masabamasaba
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplatePresentation.STUDIO
 
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...WSO2
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension AidPhilip Schwarz
 
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...masabamasaba
 
Artyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxArtyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxAnnaArtyushina1
 
WSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2
 
%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview
%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview
%in Hazyview+277-882-255-28 abortion pills for sale in Hazyviewmasabamasaba
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisamasabamasaba
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...Health
 
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...masabamasaba
 

Recently uploaded (20)

Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
 
tonesoftg
tonesoftgtonesoftg
tonesoftg
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto
 
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
Devoxx UK 2024 - Going serverless with Quarkus, GraalVM native images and AWS...
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
 
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open SourceWSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation Template
 
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
 
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
%+27788225528 love spells in Atlanta Psychic Readings, Attraction spells,Brin...
 
Artyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxArtyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptx
 
WSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go Platformless
 
%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview
%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview
%in Hazyview+277-882-255-28 abortion pills for sale in Hazyview
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
 
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
 

Interpretable Machine Learning

  • 1.
  • 2. 2 ● Applied Mathematics, Data Science ● SW Engineering, Machine Learning ● Big Data, Hadoop, Spark mspitzer@inovex.de @mspitzer243
  • 3. 3 Interpretation is the process of giving explanations to humans. ~ B. Kim, Google Brain, Interpretable Machine Learning (ICML 2017) https://people.csail.mit.edu/beenkim/papers/BeenK_FinaleDV_ICML2017_tutorial.pdf
  • 4. 4 “Interpretability is the degree to which an observer can understand the cause of a decision.” ~ Miller T., 2017, Explanation in AI: Insights from the Social Sciences ● humans create decision systems ● humans are affected by decisions ● humans demand for explanations https://arxiv.org/pdf/1706.07269.pdf
  • 5. 5 Bias towards Accuracy Do also consider asking yourself: ● Am I solving the right problem? ● How to make people trust my algorithm? ● Is there any bias? Are the training data representative? ● What is the impact in a real-world setting? https://bentoml.com/posts/2019-04-19-one-model/ “The machine learning community focuses too much on predictive performance. But machine learning models are always a small part of a complex system.” ~ C. Molnar, 2019, One Model to Rule Them All
  • 8. 8https://arxiv.org/pdf/1606.03490.pdf The additional need for interpretability The decision process of a model should be consistent to the domain knowledge of an expert. In particular, it ... ● should not encode bias ● should not pick up random correlation ● should not use leaked information hard to capture in asingle quantity
  • 9. 9 Use models that are intrinsically interpretable and known to be easy for humans to understand. Train a black box model and apply post-hoc interpretability techniques to provide explanations. 1 2
  • 10. 10 Linear Regression Linearity makes model easy to interpret ● learned weights can be used to explain feature effects ● predictions can be decomposed into individual attributions ● confidence intervals express uncertainty
  • 11. Linear Regression: Model Internals https://christophm.github.io/interpretable-ml-book/limo.html ● Coefficients indicate direction of influence ● Confidence intervals express significance and uncertainty ● Not comparable across features unless standardized
  • 12. Linear Regression: Feature Effects https://christophm.github.io/interpretable-ml-book/limo.html ● Decompose predictions into individual feature attributions ● Scale-independent, hence comparable across features ● Enables us to draw conclusions about feature importance
  • 13. https://christophm.github.io/interpretable-ml-book/limo.html Linear Regression: Feature Effects ● Decompose predictions into individual feature attributions ● Scale-independent, hence comparable across features ● Enables us to draw conclusions about feature importance ● Individual effects comparable to overall distribution
  • 14. 14 Decision Trees Intuitive decision process makes model easy to interpret ● captures nonlinear dependencies and interactions ● model is simple and self-describing ● rule-based prediction feels natural for humans
  • 15. 15 Decision Trees: Model Internals income > X? dept < Y? YESNO NO has larger impact than dept ● Tree structure lets us assess feature importance
  • 16. 16 Decision Trees: Model Internals income > X? dept < Y? YESNO NO ● Tree structure lets us assess feature importance ● Feature interactions can be determined by following paths from root to leaf
  • 17. 17 Decision Trees: Individual Explanations income > X? dept < Y? YESNO NO ● Tree structure lets us assess feature importance ● Feature interactions can be determined by following paths from root to leaf ● To explain a particular prediction, just take a look at the path from root to leaf
  • 18. 18 Wrap Up: Desirable Properties Intrinsically interpretable models simplify answering: ● Which features are relevant? ● How do they influence predictions? ● How do features interact? ● How certain is a prediction? Both for the entire model as well as individual predictions
  • 19. 19 Wrap Up: Desirable Properties Intrinsically interpretable models simplify answering: ● Which features are relevant? ● How do they influence predictions? ● How do features interact? ● How certain is a prediction? Both for the entire model as well as individual predictions How to answer these questions if models were black boxes?
  • 20. 20 Use models that are intrinsically interpretable and known to be easy for humans to understand. Train a black box model and apply post-hoc interpretability techniques to provide explanations. 1 2
  • 21. 21 Feature Shuffling https://amunategui.github.io/variable-importance-shuffler/ Train Model Apply Shuffle Evaluate Training Testing Shuffled Scored RMSE’=4.8 Evaluate Scored RMSE=3.2 X X’ For every Feature X: Repeat this process N times X’ = Perm(X) Degradation(RMSE,X) = 4.8 - 3.2 = 1.6
  • 23. 23 Individual Conditional Expectation (ICE) https://christophm.github.io/interpretable-ml-book/pdp.html Train Model Training Testing Overwrite Modified X Apply Scored X’ X’ = Const XFor every Feature X: Repeat this process using some constants CX ŷ
  • 24. 24 Individual Conditional Expectation (ICE) https://christophm.github.io/interpretable-ml-book/pdp.html
  • 25. 25 Individual Conditional Expectation (ICE) https://christophm.github.io/interpretable-ml-book/pdp.html
  • 26. 26 Individual Conditional Expectation (ICE) https://christophm.github.io/interpretable-ml-book/pdp.html
  • 28. ● Feeds original model with small variations of instance to be explained ● Sampled instances are weighted by proximity to the instance of interest ● Interpretable models are fit locally on observed outcome 28 Local Surrogate Models (LIME) https://christophm.github.io/interpretable-ml-book/lime.html
  • 29. 29 Local Surrogate Models (LIME) https://www.oreilly.com/learning/introduction-to-local-interpretable-model-agnostic-explanations-lime
  • 30. 30 Conclusion ● performance metrics are crucial for evaluation, but they lack explanations ● criteria like fairness and consistency are much harder if not impossible to quantify ● the problem with blackboxes is the lack of trust caused by their opaque nature ● transparency is key to achieving trust and acceptance in the mainstream
  • 32. ● Molnar C., 2018, Interpretable Machine Learning - A Guide for Making Black Box Models Explainable ● Gill N., Hall P., 2018, An Introduction to Machine Learning Interpretability ● Zhao Q., Hastie T., 2017, Causal Interpretations of Black-Box Models ● Kim B., Doshi-Velez F., 2017, Interpretable Machine Learning: The fuss, the concrete and the questions ● Ribeiro, M.T., Singh, S. and Guestrin, C., 2016, August. Why should i trust you? Explaining the predictions of any classifier 32 Resources
  • 33. 33
  • 34. Marcel Spitzer Big Data Scientist mspitzer@inovex.de inovex GmbH Schanzenstraße 6-20 Kupferhütte 1.13 51063 Köln