16. Is it fair? Is it
accountable?
What does it take to trust a decision made by a
machine?
(Other than that it is 99% accurate)?
Did anyone
tamper
with it?
#21, #32, #93
#21, #32, #93
Is it easy to
understand?
@MargrietGr
17. Is it fair? Is it
accountable?
What does it take to trust a decision made by a
machine?
Did anyone
tamper
with it?
#21, #32, #93
#21, #32, #93
Is it easy to
understand?
@MargrietGr
20. Misclassification
Adversarial machine learning
Adversarial machine learning can be used to “trick” machine learning models into providing
incorrect predictions
https://www.ibm.com/blogs/research/2018/04/ai-adversarial-robustness-toolbox/
27. Is it fair? Is it
accountable?
What does it take to trust a decision made by a
machine?
Did anyone
tamper
with it?
#21, #32, #93
#21, #32, #93
Is it easy to
understand?
@MargrietGr
28. Criminal Justice System
Risk scores using
Northpointe’s COMPAS
algorithm.
Defendants with low risk
scores are released on
bail.
It falsely flagged black
defendants as future
criminals, wrongly
labeling them this way at
almost twice the rate as
white defendants
https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
.
@MargrietGr
35. Is it fair? Is it
accountable?
What does it take to trust a decision made by a
machine?
Did anyone
tamper
with it?
#21, #32, #93
#21, #32, #93
Is it easy to
understand?
@MargrietGr
36. AIX360
AI Explainability 360
↳ (AIX360)
https://github.com/IBM/AIX360
Toolbox
Local post-hoc
Global post-hoc
Directly interpretable
http://aix360.mybluemix.net
@MargrietGr
37. AIX360: Different Ways
to explain
End users/customers (trust)
Doctors: Why did you recommend this treatment?
Customers: Why was my loan denied?
Teachers: Why was my teaching evaluated in this
way?
@MargrietGr
38. AIX360: Different Ways
to explain
End users/customers (trust)
Doctors: Why did you recommend this treatment?
Customers: Why was my loan denied?
Teachers: Why was my teaching evaluated in this
way?
Gov’t/regulators (compliance, safety)
Prove to me that you didn't discriminate.
@MargrietGr
39. AIX360: Different Ways
to explain
End users/customers (trust)
Doctors: Why did you recommend this treatment?
Customers: Why was my loan denied?
Teachers: Why was my teaching evaluated in this
way?
Gov’t/regulators (compliance, safety)
Prove to me that you didn't discriminate.
Developers (quality, “debuggability”)
Is our system performing well?
How can we improve it?
@MargrietGr
46. Is it fair? Is it
accountable?
What does it take to trust a decision made by a
machine?
(Other than that it is 99% accurate)?
Did anyone
tamper
with it?
#21, #32, #93
#21, #32, #93
Is it easy to
understand?
@MargrietGr
47. FAIRNESS EXPLAINABILITYROBUSTNESS LINEAGE
Trusted AI Lifecycle through Open Source
Adversarial
Robustness 360
↳ (ART)
AI Fairness
360
↳ (AIF360)
AI Explainability
360
↳ (AIX360)
github.com/IBM/adversa
rial-robustness-toolbox
art-demo.mybluemix.net
github.com/IBM/AIF360
aif360.mybluemix.net
• github.com/IBM/AIX360
aix360.mybluemix.net
In the works!
Is it fair?
Is it easy to
understand?
Is it accountable?
Did anyone
tamper with it?
@MargrietGr
53. @MargrietGr
3RD PARTY IDE &
FRAMEWORKS
Watson OpenScale
Automated Anomaly and
Drift detection
Business KPIs
Watson Studio
Watson Machine
Learning
3RD PARTY RUNTIMES
Build Deploy and run Operate trusted AI
Fairness and Explainability
Inputs for Continuous
Evolution
Accuracy
Validation and Feedback
SPSS Modeler
Custom (Kubernetes etc.)
Microsoft Azure ML
Amazon Web Services
Keras
Pytorch
Scikit-learn
Spark ML
Caffe2 …
Free IBM Cloud account: ibm.biz/BdzLdz
54. Provision services Watson Studio
Cloud Object Store
Watson Machine Learning
Watson OpenScale
@MargrietGr
56. Provision services
Setup a project
Deploy pre-trained
model
Watson Studio
Jupyter notebooks
SparkML model
Deploy as API
Test API
@MargrietGr
57. Provision services
Setup a project
Deploy pre-trained
model
Configure monitoring
Watson Studio + OpenScale
Jupyter notebooks + UI
Set up datamart
Subscribe to monitoring of deployed model
- Quality and explainability
- Fairness
- Drift
@MargrietGr
69. Recap
@MargrietGr
Add trust by asking these questions
Did anyone tamper with it?
Is it fair?
Is it easy to understand?
Is it accountable?
AI is a systems architecture with lots of
moving parts
It is cool
It is state of the art
It is exciting to build new applications
It is not magic
It is not intelligent