SlideShare a Scribd company logo
1 of 47
Download to read offline
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Explainable AI
for ordinary humans
Teresa Kubacka, PhD
www.teresa-kubacka.com
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Translating
between humans
and computers
What will this talk be about?
Differential equations
Philosophy of trust
Terminator
Comprehensive,
end-to-end overview
of a domain given by
a Nobel laureate
How to save the world
Cool charts
Looking into
the kitchen
Inspiring
examples Mess
People
Becoming a
bit nerdy
Symbiosis
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
During the talk we will...
- Explore the problem: what is Explainable AI (XAI)?
- Build our own AI
- Explore the symbiosis between data work and UX design
- Look at some practical strategies around explainability
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What is XAI?
It depends!
(It’s a mess…)
(...but a beautiful and exciting mess!)
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What do people think?
Explainable is a
synonym to...
Interpretable
Reproducible
Responsible
Tested
Fair
Auditable
Accountable
Certifiable
Inspectable
Justifiable
Operational
Ready-to-Use
Reliable
Repeatable
Self-service
Transparent
Trusted
Unbiased
Understandable
Verifiable
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What do people need it for?
http://aix360.mybluemix.net/consumer
IBM Research Case Study: AI-powered credit approval system
Audit and report if the model is treating
different subgroups “fairly”
Check stability of the models predictions
Cross-check if the features make sense
Introduce improvements to the model
Actively monitor model performance
...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Data scientist’s view on XAI
https://www.kaggle.com/dansbecker/advanced-uses-of-shap-values https://fredhohman.com/papers/chameleon
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Everybody else
https://www.kaggle.com/dansbecker/advanced-uses-of-shap-values https://fredhohman.com/papers/chameleon
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What is XAI?
It looks like what XAI is has a lot to do with humans!
(It’s a mess…)
(...but a mess we know how to deal with!)
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Let’s go back a step
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What is AI?
https://developer.nvidia.com/discover/convolutional-neural-network
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What is machine learning?
data
rules
resultscomputation
Traditional programming
data
rules
results
Machine learning
computation
Training the model = process of
discovering the rules
Data, results = sets of numbers
Rules = mathematical transformations
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Let’s do it together!
% nuts
price
Let’s build a cookie classifier!
https://medium.com/@kozyrkov/machine-learning-is-the-emperor-wearing-clothes-928fe406fe09
Example borrowed from Cassie Kozyrkov
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Let’s do it together!
Maybe it’s a cookie with goji berries?
Or maybe I wrote down 9 instead of 3?
% nuts
price
Let’s build a cookie classifier!
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Find a line separating the two classes
Decision
trees
SVMs Neural
nets
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Pick the best line
Train the model
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Pick the best line
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Count the mistakes
Y N
Y 11 2
N 1 17
Predicted
Ground Truth
Confusion Matrix: false positives,
false negatives, sensitivity,
precision, specificity, accuracy…
Test Set vs Train Set: Hold out
some “fresh” data for this!
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Save the model
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Use the model on new data
?
? N
Prediction:
Confidence: how sure is the
model about this prediction
What could explainability mean here?
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Translating between the two worlds
Human
reality
Mathematical
model
Will I like
them?
ML
Classifier
Cookies
Set of
numbers
Model
prediction
Probably
not
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Translating between the two worlds
Human
reality
Mathematical
model
Use case,
problem
ML task
Reality
Data Numerical
result
Insight
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
For XAI, I need to translate again
Human
reality
Mathematical
model
Use case,
problem
ML task
Reality
Data Numerical
result
Insight Why
Algorithm Numerical
result
Explanation
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
The most important question is about people
Human
reality
Mathematical
model
Use case,
problem
ML task
Reality
Data Numerical
result
Insight Why
Algorithm Numerical
result
Explanation
Did it increase reliability, trust, safety?
Did it influence what a user did?
If we can design AI which is “reliable, trusted,
and safe” we can dramatically enhance human
performance in the coming decade.
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
- Data is never a perfect representation of reality
- There is never a clear boundary - there are always points that are
misidentified
- Different algorithms will make their “decision” using different
criteria
- There may be more to “explain” than the algorithm itself (data
collection, training process etc.)
- If there is a signal, AI will pick it up
What does it mean for us?
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
AI is really stupid
https://www.topbots.com/chihuahua-muffin-searching-best-computer-vision-api/
https://arxiv.org/abs/1602.04938
https://deepai.org/publication/understanding-unequal-gender-classification-accuracy-from-face-images
It only sees a surface It can be very confident for a
wrong reason
If there is a signal, it will find it
Wolf → White background detector Gender → Make-up detector
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What can we do?
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
What can we do?
Interrogate the model
What did you notice?
What did you think?
Work with the context
and borrow best practices
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
“What did you notice?” Feature importances, activation maps,
saliency maps, attributions, feature maps
Cookie classifier:
- % nuts
- price
- % raisins
- producer
- size
- density
- sweetness
- # chocolate chips
- % seeds
- ...
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
Prediction:
I would like it
Input new cookie:
3% nuts, 1.5 CHF,
20% raisins...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
“What did you notice?” Feature importances, activation maps,
saliency maps, attributions, feature maps
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
LIME: locally
interpretable
explanations
Shapley
values / SHAP:
game theory
Attention, anchors, distillation,
randomized input sampling...
Many clever methods to get these numbers
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
It also works for images...
https://arxiv.org/abs/1806.07421
http://shared-interest.csail.mit.edu
Shared Interest - Saliency
Explorer (MIT)
Such insights are actionable!
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
...and for text
https://arxiv.org/abs/2009.05818 Classifying reviews,
detecting emotions,
automatizing client
complaints, triaging
documents...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Information visualization matters
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Information visualization matters
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Information visualization matters
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Information visualization matters
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
Maybe I’m a cookie domain
expert and expect
sweetness to be important
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Information visualization matters
Explanation:
- % nuts: 60
- price: 10
- % raisins: 13
- producer: 2
- size: 7
- density: 22
- sweetness: 10
- # chocolate chips: 90
- % seeds: 21
- ...
Maybe I’m a cookie domain
expert and expect
sweetness to be important
Maybe I am visually impaired and need completely another
form of accessible data visualization?
Maybe in my daily work I always use a particular chart type?
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Context: is 3.6 good or bad?
Measurement
Range, Unit -
Context
Accuracy -
Uncertainty
Danger -
Context
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
https://www.youtube.com/watch?v=pdUTdaZpses
David McCandless /
Information is Beautiful
Context and baselines
Baseline could be statistical,
or it could be another example
that you can compare to
(error bars!)
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Leverage mental models
https://www.youtube.com/watch?v=a7dhEpx6tfE
Jack the Checker
(Evelyn Muenster /
Chart Doktor)
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Many AI use cases are like medical tests
Am I pregnant?
Am I eligible for a mortgage?
Is this transaction fraudulent?
Will my customer terminate the subscription?
Is this person a likely reoffender?
...
How does my
pregnancy test work?
Am I pregnant,
if the test result was X?
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
https://www.bmj.com/content/369/bmj.m1808
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
https://www.bmj.com/content/369/bmj.m1808
...And you could think that since medical tests
are so common, we can explain them well!
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Some strategies
- Interrogate the model
- Leverage context
- Leverage information visualization
- Leverage existing approaches
- Leverage mental models
- ...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Take home message
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
(X)AI is a mess AI is stupid
But it is still very useful!
Make friends with your
fellow data scientists
And...
www.teresa-kubacka.com
World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020
Thank you!
www.teresa-kubacka.com
info@teresa-kubacka.com

More Related Content

Similar to Explainable AI for Ordinary Humans - Teresa Kubacka

Show me my data and I will tell you who I am Strata Data 2017
Show me my data and I will tell you who I am Strata Data 2017Show me my data and I will tell you who I am Strata Data 2017
Show me my data and I will tell you who I am Strata Data 2017Majken Sander
 
BI, AI/ML, Use Cases, Business Impact and how to get started
BI, AI/ML, Use Cases, Business Impact and how to get startedBI, AI/ML, Use Cases, Business Impact and how to get started
BI, AI/ML, Use Cases, Business Impact and how to get startedKarthick S
 
Understanding the New World of Cognitive Computing
Understanding the New World of Cognitive ComputingUnderstanding the New World of Cognitive Computing
Understanding the New World of Cognitive ComputingDATAVERSITY
 
Berkeley innovation forum 20171025 v1
Berkeley innovation forum 20171025 v1Berkeley innovation forum 20171025 v1
Berkeley innovation forum 20171025 v1ISSIP
 
WidasConcepts_Shortprofile
WidasConcepts_ShortprofileWidasConcepts_Shortprofile
WidasConcepts_ShortprofileVishwa Kiran
 
Benefiting from Semantic AI along the data life cycle
Benefiting from Semantic AI along the data life cycleBenefiting from Semantic AI along the data life cycle
Benefiting from Semantic AI along the data life cycleMartin Kaltenböck
 
Alcune lezioni che ho imparato negli ultimi due anni
Alcune lezioni che ho imparato negli ultimi due anniAlcune lezioni che ho imparato negli ultimi due anni
Alcune lezioni che ho imparato negli ultimi due anniBetter Software
 
Automation, intelligence and knowledge modelling
Automation, intelligence and knowledge modellingAutomation, intelligence and knowledge modelling
Automation, intelligence and knowledge modellingVeselin Pizurica
 
Future 20171110 v14
Future 20171110 v14Future 20171110 v14
Future 20171110 v14ISSIP
 
Professional AI projects the easy way slides
Professional AI projects the easy way slidesProfessional AI projects the easy way slides
Professional AI projects the easy way slidesNuSpace
 
Customer Engagement Reimagined - AI and ML Solution
Customer Engagement Reimagined - AI and ML SolutionCustomer Engagement Reimagined - AI and ML Solution
Customer Engagement Reimagined - AI and ML SolutionSagittarius
 
Every angle jacques adriaansen
Every angle   jacques adriaansenEvery angle   jacques adriaansen
Every angle jacques adriaansenBigDataExpo
 
Enterprise 2.0 und E-Collaboration
Enterprise 2.0 und E-CollaborationEnterprise 2.0 und E-Collaboration
Enterprise 2.0 und E-CollaborationMartin Koser
 
10-Hot-Data-Analytics-Tre-8904178.ppsx
10-Hot-Data-Analytics-Tre-8904178.ppsx10-Hot-Data-Analytics-Tre-8904178.ppsx
10-Hot-Data-Analytics-Tre-8904178.ppsxSangeetaTripathi8
 
AI, Machine Learning, and Data Science Concepts
AI, Machine Learning, and Data Science ConceptsAI, Machine Learning, and Data Science Concepts
AI, Machine Learning, and Data Science ConceptsDan O'Leary
 
Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...
Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...
Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...Valéry BERNARD
 
Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?
Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?
Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?BigDataExpo
 

Similar to Explainable AI for Ordinary Humans - Teresa Kubacka (20)

Show me my data and I will tell you who I am Strata Data 2017
Show me my data and I will tell you who I am Strata Data 2017Show me my data and I will tell you who I am Strata Data 2017
Show me my data and I will tell you who I am Strata Data 2017
 
BI, AI/ML, Use Cases, Business Impact and how to get started
BI, AI/ML, Use Cases, Business Impact and how to get startedBI, AI/ML, Use Cases, Business Impact and how to get started
BI, AI/ML, Use Cases, Business Impact and how to get started
 
Understanding the New World of Cognitive Computing
Understanding the New World of Cognitive ComputingUnderstanding the New World of Cognitive Computing
Understanding the New World of Cognitive Computing
 
Berkeley innovation forum 20171025 v1
Berkeley innovation forum 20171025 v1Berkeley innovation forum 20171025 v1
Berkeley innovation forum 20171025 v1
 
WidasConcepts_Shortprofile
WidasConcepts_ShortprofileWidasConcepts_Shortprofile
WidasConcepts_Shortprofile
 
Benefiting from Semantic AI along the data life cycle
Benefiting from Semantic AI along the data life cycleBenefiting from Semantic AI along the data life cycle
Benefiting from Semantic AI along the data life cycle
 
Alcune lezioni che ho imparato negli ultimi due anni
Alcune lezioni che ho imparato negli ultimi due anniAlcune lezioni che ho imparato negli ultimi due anni
Alcune lezioni che ho imparato negli ultimi due anni
 
Data, meta data, knowledge & intelligence
Data, meta data, knowledge & intelligenceData, meta data, knowledge & intelligence
Data, meta data, knowledge & intelligence
 
Automation, intelligence and knowledge modelling
Automation, intelligence and knowledge modellingAutomation, intelligence and knowledge modelling
Automation, intelligence and knowledge modelling
 
Future 20171110 v14
Future 20171110 v14Future 20171110 v14
Future 20171110 v14
 
Professional AI projects the easy way slides
Professional AI projects the easy way slidesProfessional AI projects the easy way slides
Professional AI projects the easy way slides
 
Customer Engagement Reimagined - AI and ML Solution
Customer Engagement Reimagined - AI and ML SolutionCustomer Engagement Reimagined - AI and ML Solution
Customer Engagement Reimagined - AI and ML Solution
 
Every angle jacques adriaansen
Every angle   jacques adriaansenEvery angle   jacques adriaansen
Every angle jacques adriaansen
 
Enterprise 2.0 und E-Collaboration
Enterprise 2.0 und E-CollaborationEnterprise 2.0 und E-Collaboration
Enterprise 2.0 und E-Collaboration
 
10-Hot-Data-Analytics-Tre-8904178.ppsx
10-Hot-Data-Analytics-Tre-8904178.ppsx10-Hot-Data-Analytics-Tre-8904178.ppsx
10-Hot-Data-Analytics-Tre-8904178.ppsx
 
AI, Machine Learning, and Data Science Concepts
AI, Machine Learning, and Data Science ConceptsAI, Machine Learning, and Data Science Concepts
AI, Machine Learning, and Data Science Concepts
 
Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...
Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...
Artificial Intelligence for Travel - MyLittleAdventure / Welcome City Lab Dem...
 
SSE 2017 10-09
SSE 2017 10-09SSE 2017 10-09
SSE 2017 10-09
 
Introduzione
IntroduzioneIntroduzione
Introduzione
 
Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?
Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?
Fontys - Demystify AI. Wat is er mogelijk met AI en wat niet?
 

Recently uploaded

Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfSocial Samosa
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystSamantha Rae Coolbeth
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改atducpo
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiSuhani Kapoor
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130Suhani Kapoor
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 

Recently uploaded (20)

Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data Analyst
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 

Explainable AI for Ordinary Humans - Teresa Kubacka

  • 1. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Explainable AI for ordinary humans Teresa Kubacka, PhD www.teresa-kubacka.com
  • 2. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Translating between humans and computers What will this talk be about? Differential equations Philosophy of trust Terminator Comprehensive, end-to-end overview of a domain given by a Nobel laureate How to save the world Cool charts Looking into the kitchen Inspiring examples Mess People Becoming a bit nerdy Symbiosis
  • 3. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 During the talk we will... - Explore the problem: what is Explainable AI (XAI)? - Build our own AI - Explore the symbiosis between data work and UX design - Look at some practical strategies around explainability
  • 4. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What is XAI? It depends! (It’s a mess…) (...but a beautiful and exciting mess!)
  • 5. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What do people think? Explainable is a synonym to... Interpretable Reproducible Responsible Tested Fair Auditable Accountable Certifiable Inspectable Justifiable Operational Ready-to-Use Reliable Repeatable Self-service Transparent Trusted Unbiased Understandable Verifiable
  • 6. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What do people need it for? http://aix360.mybluemix.net/consumer IBM Research Case Study: AI-powered credit approval system Audit and report if the model is treating different subgroups “fairly” Check stability of the models predictions Cross-check if the features make sense Introduce improvements to the model Actively monitor model performance ...
  • 7. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Data scientist’s view on XAI https://www.kaggle.com/dansbecker/advanced-uses-of-shap-values https://fredhohman.com/papers/chameleon
  • 8. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Everybody else https://www.kaggle.com/dansbecker/advanced-uses-of-shap-values https://fredhohman.com/papers/chameleon
  • 9. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What is XAI? It looks like what XAI is has a lot to do with humans! (It’s a mess…) (...but a mess we know how to deal with!)
  • 10. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Let’s go back a step
  • 11. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What is AI? https://developer.nvidia.com/discover/convolutional-neural-network
  • 12. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What is machine learning? data rules resultscomputation Traditional programming data rules results Machine learning computation Training the model = process of discovering the rules Data, results = sets of numbers Rules = mathematical transformations
  • 13. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Let’s do it together! % nuts price Let’s build a cookie classifier! https://medium.com/@kozyrkov/machine-learning-is-the-emperor-wearing-clothes-928fe406fe09 Example borrowed from Cassie Kozyrkov
  • 14. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Let’s do it together! Maybe it’s a cookie with goji berries? Or maybe I wrote down 9 instead of 3? % nuts price Let’s build a cookie classifier!
  • 15. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Find a line separating the two classes Decision trees SVMs Neural nets
  • 16. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Pick the best line Train the model
  • 17. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Pick the best line
  • 18. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Count the mistakes Y N Y 11 2 N 1 17 Predicted Ground Truth Confusion Matrix: false positives, false negatives, sensitivity, precision, specificity, accuracy… Test Set vs Train Set: Hold out some “fresh” data for this!
  • 19. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Save the model
  • 20. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Use the model on new data ? ? N Prediction: Confidence: how sure is the model about this prediction What could explainability mean here?
  • 21. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Translating between the two worlds Human reality Mathematical model Will I like them? ML Classifier Cookies Set of numbers Model prediction Probably not
  • 22. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Translating between the two worlds Human reality Mathematical model Use case, problem ML task Reality Data Numerical result Insight
  • 23. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 For XAI, I need to translate again Human reality Mathematical model Use case, problem ML task Reality Data Numerical result Insight Why Algorithm Numerical result Explanation
  • 24. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 The most important question is about people Human reality Mathematical model Use case, problem ML task Reality Data Numerical result Insight Why Algorithm Numerical result Explanation Did it increase reliability, trust, safety? Did it influence what a user did? If we can design AI which is “reliable, trusted, and safe” we can dramatically enhance human performance in the coming decade.
  • 25. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 - Data is never a perfect representation of reality - There is never a clear boundary - there are always points that are misidentified - Different algorithms will make their “decision” using different criteria - There may be more to “explain” than the algorithm itself (data collection, training process etc.) - If there is a signal, AI will pick it up What does it mean for us?
  • 26. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 AI is really stupid https://www.topbots.com/chihuahua-muffin-searching-best-computer-vision-api/ https://arxiv.org/abs/1602.04938 https://deepai.org/publication/understanding-unequal-gender-classification-accuracy-from-face-images It only sees a surface It can be very confident for a wrong reason If there is a signal, it will find it Wolf → White background detector Gender → Make-up detector
  • 27. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What can we do?
  • 28. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 What can we do? Interrogate the model What did you notice? What did you think? Work with the context and borrow best practices
  • 29. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 “What did you notice?” Feature importances, activation maps, saliency maps, attributions, feature maps Cookie classifier: - % nuts - price - % raisins - producer - size - density - sweetness - # chocolate chips - % seeds - ... Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ... Prediction: I would like it Input new cookie: 3% nuts, 1.5 CHF, 20% raisins...
  • 30. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 “What did you notice?” Feature importances, activation maps, saliency maps, attributions, feature maps Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ... LIME: locally interpretable explanations Shapley values / SHAP: game theory Attention, anchors, distillation, randomized input sampling... Many clever methods to get these numbers
  • 31. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 It also works for images... https://arxiv.org/abs/1806.07421 http://shared-interest.csail.mit.edu Shared Interest - Saliency Explorer (MIT) Such insights are actionable!
  • 32. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 ...and for text https://arxiv.org/abs/2009.05818 Classifying reviews, detecting emotions, automatizing client complaints, triaging documents...
  • 33. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Information visualization matters Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ...
  • 34. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Information visualization matters Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ...
  • 35. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Information visualization matters Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ...
  • 36. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Information visualization matters Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ... Maybe I’m a cookie domain expert and expect sweetness to be important
  • 37. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Information visualization matters Explanation: - % nuts: 60 - price: 10 - % raisins: 13 - producer: 2 - size: 7 - density: 22 - sweetness: 10 - # chocolate chips: 90 - % seeds: 21 - ... Maybe I’m a cookie domain expert and expect sweetness to be important Maybe I am visually impaired and need completely another form of accessible data visualization? Maybe in my daily work I always use a particular chart type?
  • 38. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Context: is 3.6 good or bad? Measurement Range, Unit - Context Accuracy - Uncertainty Danger - Context
  • 39. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 https://www.youtube.com/watch?v=pdUTdaZpses David McCandless / Information is Beautiful Context and baselines Baseline could be statistical, or it could be another example that you can compare to (error bars!)
  • 40. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Leverage mental models https://www.youtube.com/watch?v=a7dhEpx6tfE Jack the Checker (Evelyn Muenster / Chart Doktor)
  • 41. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Many AI use cases are like medical tests Am I pregnant? Am I eligible for a mortgage? Is this transaction fraudulent? Will my customer terminate the subscription? Is this person a likely reoffender? ... How does my pregnancy test work? Am I pregnant, if the test result was X?
  • 42. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 https://www.bmj.com/content/369/bmj.m1808
  • 43. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 https://www.bmj.com/content/369/bmj.m1808 ...And you could think that since medical tests are so common, we can explain them well!
  • 44. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Some strategies - Interrogate the model - Leverage context - Leverage information visualization - Leverage existing approaches - Leverage mental models - ...
  • 45. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Take home message
  • 46. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 (X)AI is a mess AI is stupid But it is still very useful! Make friends with your fellow data scientists And...
  • 47. www.teresa-kubacka.com World Usability Day 2020 Switzerland – Human-Centered AI – 12.11.2020 Thank you! www.teresa-kubacka.com info@teresa-kubacka.com