191120-trustedai-margriet-191120112913

pdf

School

Villanova University *

*We aren’t endorsed by this school

Course

21

Subject

Computer Science

Date

Nov 24, 2024

Type

pdf

Pages

70

Uploaded by versalas23a

Report
Trusting machines with robust, unbiased and reproducible AI — Dr. Margriet Groenendijk Data & AI Developer Advocate
@MargrietGr https://arxiv.org/abs/1710.10196
Deep Learning – Imaginary celebrities @MargrietGr https://arxiv.org/abs/1710.10196
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
@MargrietGr
Do you trust AI? @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Do you trust AI? Why? @MargrietGr
"AI is the state of the art of computers, but calling it intelligence bothers me” @ stevewoz #GOTOcph @MargrietGr
Machine learning Algorithm selection Deep learning Neural network design Artificial intelligence Systems architecture @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
AI is used in many high-stakes decision making applications Credit Employment Admission Healthcare Sentencing @MargrietGr
@MargrietGr https://slate.com/business/2018/10/amazon-artificial- intelligence-hiring-discrimination-women.html
Gender Shades Project Released February 2018 @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr http://www.aies-conference.com/wp- content/uploads/2019/01/AIES-19_paper_223.pdf
@MargrietGr https://www.wired.com/story/the-apple-card-didnt-see-genderand-thats-the-problem/
Let’s increase our trust @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
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
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
https://hackernoon.com/dogs-wolves-data-science-and-why-machines-must-learn-like- humans-do-41c43bc7f982 @MargrietGr
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/
https://bigcheck.mybluemix.net
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
https://arxiv.org/pdf/1707.08945.pdf
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Self Driving Vehicles
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Adversarial threats to AI Evasion attacks Performed at test time Perturb inputs with noise Model fails to predict correctly Undetectable by humans
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Adversarial threats to AI Poisoning attacks Performed at training time Insert poisoned sample in training data Use backdoor later
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
ART Adversarial Robustness 360 Toolbox ↳ (ART) https://github.com/IBM/adversarial-robustness-toolbox 28 Toolbox Evasion attacks Defense methods Detection methods Robustness metrics https://art-demo.mybluemix.net/
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
AIF360 AI Fairness 360 ↳ (AIF360) https://github.com/IBM/AIF360 31 Toolbox Fairness metrics (70+) Fairness metric explanations Bias mitigation algorithms (10+) http://aif360.mybluemix.net/
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aif360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aif360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aif360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aif360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aif360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
AIX360 AI Explainability 360 ↳ (AIX360) https://github.com/IBM/AIX360 Toolbox Local post-hoc Global post-hoc Directly interpretable http://aix360.mybluemix.net @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aix360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aix360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aix360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aix360.mybluemix.net/ @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
http://aix360.mybluemix.net/
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
FAIRNESS EXPLAINABILITY ROBUSTNESS 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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
From algorithm to application @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr Output Credit Risk Model Train Algorithm John X § credit_score=800 § age=25 § income=$900,000 § works in Oil & Gas Historical Loans Label No Risk Example: credit risk
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr No Risk Output Risk James Y § credit_score=900 § age=55 § income=$1,200,000 § works in Insurance New Applicant Credit Risk Model Example: credit risk
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr 3 RD PARTY IDE & FRAMEWORKS Watson OpenScale Automated Anomaly and Drift detection Business KPIs Watson Studio Watson Machine Learning 3 RD 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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Provision services Watson Studio Cloud Object Store Watson Machine Learning Watson OpenScale @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Provision services Setup a project Watson Studio Jupyter notebooks @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Provision services Setup a project Deploy pre-trained model Watson Studio Jupyter notebooks SparkML model Deploy as API Test API @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
@MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Drift @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Drift @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Provision services Setup a project Deploy pre-trained model Configure monitoring Use in production @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
https://ibm.biz/ digitaldevcon @MargrietGr
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
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
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Resources @MargrietGr Models ibm.biz/model-exchange Data ibm.biz/data-exchange IBM Cloud ibm.biz/BdzLdz Slides ibm.biz/slides-margriet Patterns and Tutorials https://developer.ibm.com
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help

Related Documents

Screenshot_2023-12-13-18-03-22-24_13_12_2023_18_09.png
D-PST-DY-23 Dell PowerStore Deploy 2023 Exam Questions.pdf
EE5731_Questions_updated_30-30.pdf
CS4248_Tutorial_2.pdf
Formative Quiz Operations with Functions.docx
Lecture - 18 - 19.pptx
CIS256_1.7_InstallNewForest_Corey_Adams.docx
CIS 7030 Geospatial Analysis Assignment (2023).docx
photo_18_2024-02-15_13-41-00.jpg
stack4.py
Screenshot 2023-12-20 9.59.41 PM.png
AI Assignment (1).doc
Recommended textbooks for you
Text book image
MIS
Computer Science
ISBN:9781337681919
Author:BIDGOLI
Publisher:Cengage
Text book image
Principles of Information Systems (MindTap Course...
Computer Science
ISBN:9781285867168
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Text book image
Principles of Information Systems (MindTap Course...
Computer Science
ISBN:9781305971776
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Text book image
Fundamentals of Information Systems
Computer Science
ISBN:9781337097536
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Text book image
Enhanced Discovering Computers 2017 (Shelly Cashm...
Computer Science
ISBN:9781305657458
Author:Misty E. Vermaat, Susan L. Sebok, Steven M. Freund, Mark Frydenberg, Jennifer T. Campbell
Publisher:Cengage Learning
Text book image
Fundamentals of Information Systems
Computer Science
ISBN:9781305082168
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
SEE MORE TEXTBOOKS
Recommended textbooks for you
Text book image
MIS
Computer Science
ISBN:9781337681919
Author:BIDGOLI
Publisher:Cengage
Text book image
Principles of Information Systems (MindTap Course...
Computer Science
ISBN:9781285867168
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Text book image
Principles of Information Systems (MindTap Course...
Computer Science
ISBN:9781305971776
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Text book image
Fundamentals of Information Systems
Computer Science
ISBN:9781337097536
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Text book image
Enhanced Discovering Computers 2017 (Shelly Cashm...
Computer Science
ISBN:9781305657458
Author:Misty E. Vermaat, Susan L. Sebok, Steven M. Freund, Mark Frydenberg, Jennifer T. Campbell
Publisher:Cengage Learning
Text book image
Fundamentals of Information Systems
Computer Science
ISBN:9781305082168
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
SEE MORE TEXTBOOKS