SlideShare a Scribd company logo
1 of 17
BUILDING INTELLIGENT SYSTEMS
(THAT CAN EXPLAIN)
Ilaria Tiddi
KR&R group, Faculty of Computer Science, VU Amsterdam
Cooperation Lab, Faculty of Behavioural and Movement Sciences
VU Amsterdam
Disclaimer
This is NOT a presentation on eXplainable AI (XAI) ...
...but rather on systems making sense of complex data
…we can argue at Q time if they somewhat overlap
● Learn new knowledge
● Find meaning : we reconcile the contradictions in our knowledge
● Socially interact : we create a shared meaning, we change/influence the
others’ beliefs
● ...and because GDPR says so
Users have a “right to explanation”
for any decisions made about them
WHY DO WE NEED (SYSTEMS THAT) EXPLAIN?
Different disciplines, common features [1]:
● Generation of coherence between old and new knowledge
● Same elements (theory, anterior, posterior, circumstances)
● Same processes (psychological , linguistic)
[1] Tiddi et al. (2015), An Ontology Design Pattern to Define Explanations, K-CAP2015
Determinists Hempel&
Oppenheim
Weber&
Durkheim
Charles
Peirce
DEFINING EXPLANATIONS (ε)
V-IV AC
Plato&Aristotle
XVII BC 1948 19641903 2015
?
Explication (⋍ Interpretation)
Justification
Explic-/Interpret-/Explainability
SOME DISAMBIGUATIONS
Explanation
ε of why a decision is good
the degree to which an observer
can understand the cause of a
decision
Which types?
● factual ε : why specific ‘everyday’ events occur
● scientific ε : generalising scientific theories
● reason ε : explaining behaviour and decision making
Which processes?
1) cognitive : determining the causes (explanans) of an event (explanandum) and
relating these to a particular context
2) social : transferring knowledge between explainer and explainee
RESEARCH GOAL : INTELLIGENT SYSTEMS THAT CAN EXPLAIN
Which audience?
● engineers/scientists/experts
● end-users
Which characteristics?
● Transparency (traceability + verificability)
● Intelligibility + explainability
Which language?
● Visual
● Written
● Spoken
RESEARCH GOAL : INTELLIGENT SYSTEMS THAT CAN EXPLAIN
Existing knowledge sources can serve as background (the “old”) knowledge to generate
explanations:
● Plenty of available sources (not only RDF...)
● Connected, centralised hubs
● Multi-domain (serendipity!)
APPROACH : REUSE AVAILABLE KNOWLEDGE SOURCES
Generating explanations from the Web of Data [2]
EXAMPLE : FACTUAL, WRITTEN ε
[2] Tiddi. (2016), Explaining Data Patterns using Knowledge from the Web of Data, Ph.D. thesis. Demo: http://dedalo.kmi.open.ac.uk/
Why do people search for “A Song of Ice
and Fire” only in certain periods?”
Explaining behaviours and recommending self-learners using online resources [3]
EXAMPLE : REASON, VISUAL ε
[3] http://afel-project.eu
Robots finding explanations for their behavior in a smart-city datahub [4]
EXAMPLE : REASON, SPOKEN ε
[4] http://sciroc.eu
[ Shameless advert ]
1st ERL Smart CIties
RObotics Challenge
16–22/09/2019
Milton Keynes,UK
No need to have a
robot!!!
Explaining scenes in motion using ShapeNet [5] as background knowledge
(and YOLO [6] for pre-processing)
EXAMPLE : factual&reason, spoken ε
[5] http://www.shapenet.org
[6] https://pjreddie.com/darknet/yolo/
Explaining neural attentions
A multi-layer LSTM network to understanding NL
robotic commands [8]
Avoid training biases using linguistic corpora
(FrameNet [7]) combined with domain-specific
datasets
EXAMPLE : REASON, VISUAL ε
[7] https://framenet.icsi.berkeley.edu/fndrupal/
[8] Mensio et al., A Multi-layer LSTM-based Approach for Robot Command Interaction Modeling, Language and Robotics (LangRobo), IROS 2018.
Explaining inconsistencies using an autonomous agent in a smart office [9]
Monitoring Health&Safety using a SHACL-based model checking and behavioural trees
Centralised data integration, processing and reasoning
EXAMPLE : FACTUAL, WRITTEN ε
[9] Bastianelli et al., Meet HanS, the Heath&Safety autonomous inspector, Posters&Demos track at ISWC 2018.
Re-coding Black Mirror [10] workshops
Bringing social&computer scientists
together to understand the threats of
their own technologies, and raise
awareness on methods explainability
Ethics by Design methodology
MACHINE EXPLANATION NEED MACHINE ETHICS
[10] https://kmitd.github.io/recoding-black-mirror/
Databank
● Collection of meta-analyses to study human cooperation
● 3.5k work on social dilemmas ( = benefitting the others vs. self-interest)
My goal
● creation of a research platform generating explanations for human
cooperation (+ search facilities)
● Generalising the methodology to Life & Medical Sciences (long-term)
WHAT ABOUT SCIENTIFIC EXPLANATIONS?
Thank YOU
Question time!
@IlaTiddi
i.tiddi@vu.nl
http://people.kmi.open.ac.uk/ilaria (changing soon)

More Related Content

Similar to Building intelligent systems (that can explain)

Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store -
Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store - Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store -
Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store - Hendrik Drachsler
 
KMD 1001 Design Brief and Ontology Task
KMD 1001 Design Brief and Ontology TaskKMD 1001 Design Brief and Ontology Task
KMD 1001 Design Brief and Ontology TaskStian Håklev
 
Swoogle: Showcasing the Significance of Semantic Search
Swoogle: Showcasing the Significance of Semantic SearchSwoogle: Showcasing the Significance of Semantic Search
Swoogle: Showcasing the Significance of Semantic SearchIDES Editor
 
Introducing CIDOC-CRM (Cch KR workshop #2.1)
Introducing CIDOC-CRM (Cch KR workshop #2.1)Introducing CIDOC-CRM (Cch KR workshop #2.1)
Introducing CIDOC-CRM (Cch KR workshop #2.1)Michele Pasin
 
A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...
A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...
A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...mlaij
 
Semantische Interoperatibiliteit Ngi 2008(Final)
Semantische Interoperatibiliteit Ngi 2008(Final)Semantische Interoperatibiliteit Ngi 2008(Final)
Semantische Interoperatibiliteit Ngi 2008(Final)Richard Claassens CIPPE
 
6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)IAESIJEECS
 
Does artificial neural network support connectivism’s assumptions?
Does artificial neural network support connectivism’s assumptions?Does artificial neural network support connectivism’s assumptions?
Does artificial neural network support connectivism’s assumptions?Alaa Al Dahdouh
 
ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...
ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...
ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...Artificial Intelligence Institute at UofSC
 
M1. sem web & ontology introd
M1. sem web & ontology introdM1. sem web & ontology introd
M1. sem web & ontology introdMichele Missikoff
 
Mining knowledge graphs to map heterogeneous relations between the internet o...
Mining knowledge graphs to map heterogeneous relations between the internet o...Mining knowledge graphs to map heterogeneous relations between the internet o...
Mining knowledge graphs to map heterogeneous relations between the internet o...IJECEIAES
 
Corneli
CorneliCorneli
Cornelianesah
 
Recruitment Based On Ontology with Enhanced Security Features
Recruitment Based On Ontology with Enhanced Security FeaturesRecruitment Based On Ontology with Enhanced Security Features
Recruitment Based On Ontology with Enhanced Security Featurestheijes
 
Semantic technologies for the Internet of Things
Semantic technologies for the Internet of Things Semantic technologies for the Internet of Things
Semantic technologies for the Internet of Things PayamBarnaghi
 
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information RetrievalKeystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information RetrievalMauro Dragoni
 
List of Journal after read the abstract.docx
List of Journal after read the abstract.docxList of Journal after read the abstract.docx
List of Journal after read the abstract.docxAdieYadie1
 
Artificial Intelligence A Modern Approach
Artificial Intelligence A Modern ApproachArtificial Intelligence A Modern Approach
Artificial Intelligence A Modern ApproachSara Perez
 

Similar to Building intelligent systems (that can explain) (20)

Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store -
Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store - Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store -
Learning Analytics Metadata Standards, xAPI recipes & Learning Record Store -
 
Dest 2010
Dest 2010Dest 2010
Dest 2010
 
PowerMagpie
PowerMagpiePowerMagpie
PowerMagpie
 
KMD 1001 Design Brief and Ontology Task
KMD 1001 Design Brief and Ontology TaskKMD 1001 Design Brief and Ontology Task
KMD 1001 Design Brief and Ontology Task
 
Swoogle: Showcasing the Significance of Semantic Search
Swoogle: Showcasing the Significance of Semantic SearchSwoogle: Showcasing the Significance of Semantic Search
Swoogle: Showcasing the Significance of Semantic Search
 
The basics of ontologies
The basics of ontologiesThe basics of ontologies
The basics of ontologies
 
Introducing CIDOC-CRM (Cch KR workshop #2.1)
Introducing CIDOC-CRM (Cch KR workshop #2.1)Introducing CIDOC-CRM (Cch KR workshop #2.1)
Introducing CIDOC-CRM (Cch KR workshop #2.1)
 
A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...
A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...
A DEVELOPMENT FRAMEWORK FOR A CONVERSATIONAL AGENT TO EXPLORE MACHINE LEARNIN...
 
Semantische Interoperatibiliteit Ngi 2008(Final)
Semantische Interoperatibiliteit Ngi 2008(Final)Semantische Interoperatibiliteit Ngi 2008(Final)
Semantische Interoperatibiliteit Ngi 2008(Final)
 
6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)
 
Does artificial neural network support connectivism’s assumptions?
Does artificial neural network support connectivism’s assumptions?Does artificial neural network support connectivism’s assumptions?
Does artificial neural network support connectivism’s assumptions?
 
ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...
ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...
ACM Hypertext and Social Media Conference Tutorial on Knowledge-infused Deep ...
 
M1. sem web & ontology introd
M1. sem web & ontology introdM1. sem web & ontology introd
M1. sem web & ontology introd
 
Mining knowledge graphs to map heterogeneous relations between the internet o...
Mining knowledge graphs to map heterogeneous relations between the internet o...Mining knowledge graphs to map heterogeneous relations between the internet o...
Mining knowledge graphs to map heterogeneous relations between the internet o...
 
Corneli
CorneliCorneli
Corneli
 
Recruitment Based On Ontology with Enhanced Security Features
Recruitment Based On Ontology with Enhanced Security FeaturesRecruitment Based On Ontology with Enhanced Security Features
Recruitment Based On Ontology with Enhanced Security Features
 
Semantic technologies for the Internet of Things
Semantic technologies for the Internet of Things Semantic technologies for the Internet of Things
Semantic technologies for the Internet of Things
 
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information RetrievalKeystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
 
List of Journal after read the abstract.docx
List of Journal after read the abstract.docxList of Journal after read the abstract.docx
List of Journal after read the abstract.docx
 
Artificial Intelligence A Modern Approach
Artificial Intelligence A Modern ApproachArtificial Intelligence A Modern Approach
Artificial Intelligence A Modern Approach
 

More from Vrije Universiteit Amsterdam

An ontology-based approach to improve the accessibility of ROS-based robotic ...
An ontology-based approach to improve the accessibility of ROS-based robotic ...An ontology-based approach to improve the accessibility of ROS-based robotic ...
An ontology-based approach to improve the accessibility of ROS-based robotic ...Vrije Universiteit Amsterdam
 
Update of time-invalid information in knowledge bases through mobile agents
Update of time-invalid information in knowledge bases through mobile agentsUpdate of time-invalid information in knowledge bases through mobile agents
Update of time-invalid information in knowledge bases through mobile agentsVrije Universiteit Amsterdam
 
Learning to assess Linked Data relationships using Genetic Programming
Learning to assess Linked Data relationships using Genetic ProgrammingLearning to assess Linked Data relationships using Genetic Programming
Learning to assess Linked Data relationships using Genetic ProgrammingVrije Universiteit Amsterdam
 
Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015
Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015
Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015Vrije Universiteit Amsterdam
 
Using Neural Networks to aggregate Linked Data rules
Using Neural Networks to aggregate Linked Data rulesUsing Neural Networks to aggregate Linked Data rules
Using Neural Networks to aggregate Linked Data rulesVrije Universiteit Amsterdam
 
Walking Linked Data: a graph traversal approach to explain clusters
Walking Linked Data: a graph traversal approach to explain clustersWalking Linked Data: a graph traversal approach to explain clusters
Walking Linked Data: a graph traversal approach to explain clustersVrije Universiteit Amsterdam
 
Dedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked DataDedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked DataVrije Universiteit Amsterdam
 

More from Vrije Universiteit Amsterdam (11)

An ontology-based approach to improve the accessibility of ROS-based robotic ...
An ontology-based approach to improve the accessibility of ROS-based robotic ...An ontology-based approach to improve the accessibility of ROS-based robotic ...
An ontology-based approach to improve the accessibility of ROS-based robotic ...
 
Answer Worskshop @ESWC2017 - Introduction
Answer Worskshop @ESWC2017 - IntroductionAnswer Worskshop @ESWC2017 - Introduction
Answer Worskshop @ESWC2017 - Introduction
 
Update of time-invalid information in knowledge bases through mobile agents
Update of time-invalid information in knowledge bases through mobile agentsUpdate of time-invalid information in knowledge bases through mobile agents
Update of time-invalid information in knowledge bases through mobile agents
 
Learning to assess Linked Data relationships using Genetic Programming
Learning to assess Linked Data relationships using Genetic ProgrammingLearning to assess Linked Data relationships using Genetic Programming
Learning to assess Linked Data relationships using Genetic Programming
 
An Ontology Design Pattern to Define Explanations
An Ontology Design Pattern to Define ExplanationsAn Ontology Design Pattern to Define Explanations
An Ontology Design Pattern to Define Explanations
 
LD4KD 2015 - Demos and tools
LD4KD 2015 - Demos and toolsLD4KD 2015 - Demos and tools
LD4KD 2015 - Demos and tools
 
Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015
Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015
Using Linked Data Traversal to Label Academic Communities - SAVE-SD2015
 
Quantifying the bias in data links
Quantifying the bias in data linksQuantifying the bias in data links
Quantifying the bias in data links
 
Using Neural Networks to aggregate Linked Data rules
Using Neural Networks to aggregate Linked Data rulesUsing Neural Networks to aggregate Linked Data rules
Using Neural Networks to aggregate Linked Data rules
 
Walking Linked Data: a graph traversal approach to explain clusters
Walking Linked Data: a graph traversal approach to explain clustersWalking Linked Data: a graph traversal approach to explain clusters
Walking Linked Data: a graph traversal approach to explain clusters
 
Dedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked DataDedalo, looking for Cluster Explanations in a labyrinth of Linked Data
Dedalo, looking for Cluster Explanations in a labyrinth of Linked Data
 

Recently uploaded

MODERN PHYSICS_REPORTING_QUANTA_.....pdf
MODERN PHYSICS_REPORTING_QUANTA_.....pdfMODERN PHYSICS_REPORTING_QUANTA_.....pdf
MODERN PHYSICS_REPORTING_QUANTA_.....pdfRevenJadePalma
 
VILLAGE ATTACHMENT For rural agriculture PPT.pptx
VILLAGE ATTACHMENT For rural agriculture  PPT.pptxVILLAGE ATTACHMENT For rural agriculture  PPT.pptx
VILLAGE ATTACHMENT For rural agriculture PPT.pptxAQIBRASOOL4
 
Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...
Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...
Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...yogeshlabana357357
 
Lubrication System in forced feed system
Lubrication System in forced feed systemLubrication System in forced feed system
Lubrication System in forced feed systemADB online India
 
Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...
Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...
Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...Sérgio Sacani
 
THE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPES
THE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPESTHE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPES
THE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPESkushbuR
 
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 RpWASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 RpSérgio Sacani
 
Tuberculosis (TB)-Notes.pdf microbiology notes
Tuberculosis (TB)-Notes.pdf microbiology notesTuberculosis (TB)-Notes.pdf microbiology notes
Tuberculosis (TB)-Notes.pdf microbiology notesjyothisaisri
 
TEST BANK for Organic Chemistry 6th Edition.pdf
TEST BANK for Organic Chemistry 6th Edition.pdfTEST BANK for Organic Chemistry 6th Edition.pdf
TEST BANK for Organic Chemistry 6th Edition.pdfmarcuskenyatta275
 
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...dkNET
 
PHOTOSYNTHETIC BACTERIA (OXYGENIC AND ANOXYGENIC)
PHOTOSYNTHETIC BACTERIA  (OXYGENIC AND ANOXYGENIC)PHOTOSYNTHETIC BACTERIA  (OXYGENIC AND ANOXYGENIC)
PHOTOSYNTHETIC BACTERIA (OXYGENIC AND ANOXYGENIC)kushbuR
 
Continuum emission from within the plunging region of black hole discs
Continuum emission from within the plunging region of black hole discsContinuum emission from within the plunging region of black hole discs
Continuum emission from within the plunging region of black hole discsSérgio Sacani
 
EU START PROJECT. START-Newsletter_Issue_4.pdf
EU START PROJECT. START-Newsletter_Issue_4.pdfEU START PROJECT. START-Newsletter_Issue_4.pdf
EU START PROJECT. START-Newsletter_Issue_4.pdfStart Project
 
family therapy psychotherapy types .pdf
family therapy psychotherapy types  .pdffamily therapy psychotherapy types  .pdf
family therapy psychotherapy types .pdfhaseebahmeddrama
 
ERTHROPOIESIS: Dr. E. Muralinath & R. Gnana Lahari
ERTHROPOIESIS: Dr. E. Muralinath & R. Gnana LahariERTHROPOIESIS: Dr. E. Muralinath & R. Gnana Lahari
ERTHROPOIESIS: Dr. E. Muralinath & R. Gnana Laharimuralinath2
 
Plasma proteins_ Dr.Muralinath_Dr.c. kalyan
Plasma proteins_ Dr.Muralinath_Dr.c. kalyanPlasma proteins_ Dr.Muralinath_Dr.c. kalyan
Plasma proteins_ Dr.Muralinath_Dr.c. kalyanmuralinath2
 
Triploidy ...............................pptx
Triploidy ...............................pptxTriploidy ...............................pptx
Triploidy ...............................pptxCherry
 
Mining Activity and Investment Opportunity in Myanmar.pptx
Mining Activity and Investment Opportunity in Myanmar.pptxMining Activity and Investment Opportunity in Myanmar.pptx
Mining Activity and Investment Opportunity in Myanmar.pptxKyawThanTint
 
Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...
Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...
Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...Ansari Aashif Raza Mohd Imtiyaz
 
The Scientific names of some important families of Industrial plants .pdf
The Scientific names of some important families of Industrial plants .pdfThe Scientific names of some important families of Industrial plants .pdf
The Scientific names of some important families of Industrial plants .pdfMohamed Said
 

Recently uploaded (20)

MODERN PHYSICS_REPORTING_QUANTA_.....pdf
MODERN PHYSICS_REPORTING_QUANTA_.....pdfMODERN PHYSICS_REPORTING_QUANTA_.....pdf
MODERN PHYSICS_REPORTING_QUANTA_.....pdf
 
VILLAGE ATTACHMENT For rural agriculture PPT.pptx
VILLAGE ATTACHMENT For rural agriculture  PPT.pptxVILLAGE ATTACHMENT For rural agriculture  PPT.pptx
VILLAGE ATTACHMENT For rural agriculture PPT.pptx
 
Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...
Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...
Soil and Water Conservation Engineering (SWCE) is a specialized field of stud...
 
Lubrication System in forced feed system
Lubrication System in forced feed systemLubrication System in forced feed system
Lubrication System in forced feed system
 
Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...
Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...
Exomoons & Exorings with the Habitable Worlds Observatory I: On the Detection...
 
THE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPES
THE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPESTHE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPES
THE GENERAL PROPERTIES OF PROTEOBACTERIA AND ITS TYPES
 
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 RpWASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
 
Tuberculosis (TB)-Notes.pdf microbiology notes
Tuberculosis (TB)-Notes.pdf microbiology notesTuberculosis (TB)-Notes.pdf microbiology notes
Tuberculosis (TB)-Notes.pdf microbiology notes
 
TEST BANK for Organic Chemistry 6th Edition.pdf
TEST BANK for Organic Chemistry 6th Edition.pdfTEST BANK for Organic Chemistry 6th Edition.pdf
TEST BANK for Organic Chemistry 6th Edition.pdf
 
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
 
PHOTOSYNTHETIC BACTERIA (OXYGENIC AND ANOXYGENIC)
PHOTOSYNTHETIC BACTERIA  (OXYGENIC AND ANOXYGENIC)PHOTOSYNTHETIC BACTERIA  (OXYGENIC AND ANOXYGENIC)
PHOTOSYNTHETIC BACTERIA (OXYGENIC AND ANOXYGENIC)
 
Continuum emission from within the plunging region of black hole discs
Continuum emission from within the plunging region of black hole discsContinuum emission from within the plunging region of black hole discs
Continuum emission from within the plunging region of black hole discs
 
EU START PROJECT. START-Newsletter_Issue_4.pdf
EU START PROJECT. START-Newsletter_Issue_4.pdfEU START PROJECT. START-Newsletter_Issue_4.pdf
EU START PROJECT. START-Newsletter_Issue_4.pdf
 
family therapy psychotherapy types .pdf
family therapy psychotherapy types  .pdffamily therapy psychotherapy types  .pdf
family therapy psychotherapy types .pdf
 
ERTHROPOIESIS: Dr. E. Muralinath & R. Gnana Lahari
ERTHROPOIESIS: Dr. E. Muralinath & R. Gnana LahariERTHROPOIESIS: Dr. E. Muralinath & R. Gnana Lahari
ERTHROPOIESIS: Dr. E. Muralinath & R. Gnana Lahari
 
Plasma proteins_ Dr.Muralinath_Dr.c. kalyan
Plasma proteins_ Dr.Muralinath_Dr.c. kalyanPlasma proteins_ Dr.Muralinath_Dr.c. kalyan
Plasma proteins_ Dr.Muralinath_Dr.c. kalyan
 
Triploidy ...............................pptx
Triploidy ...............................pptxTriploidy ...............................pptx
Triploidy ...............................pptx
 
Mining Activity and Investment Opportunity in Myanmar.pptx
Mining Activity and Investment Opportunity in Myanmar.pptxMining Activity and Investment Opportunity in Myanmar.pptx
Mining Activity and Investment Opportunity in Myanmar.pptx
 
Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...
Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...
Molecular and Cellular Mechanism of Action of Hormones such as Growth Hormone...
 
The Scientific names of some important families of Industrial plants .pdf
The Scientific names of some important families of Industrial plants .pdfThe Scientific names of some important families of Industrial plants .pdf
The Scientific names of some important families of Industrial plants .pdf
 

Building intelligent systems (that can explain)

  • 1. BUILDING INTELLIGENT SYSTEMS (THAT CAN EXPLAIN) Ilaria Tiddi KR&R group, Faculty of Computer Science, VU Amsterdam Cooperation Lab, Faculty of Behavioural and Movement Sciences VU Amsterdam
  • 2. Disclaimer This is NOT a presentation on eXplainable AI (XAI) ... ...but rather on systems making sense of complex data …we can argue at Q time if they somewhat overlap
  • 3. ● Learn new knowledge ● Find meaning : we reconcile the contradictions in our knowledge ● Socially interact : we create a shared meaning, we change/influence the others’ beliefs ● ...and because GDPR says so Users have a “right to explanation” for any decisions made about them WHY DO WE NEED (SYSTEMS THAT) EXPLAIN?
  • 4. Different disciplines, common features [1]: ● Generation of coherence between old and new knowledge ● Same elements (theory, anterior, posterior, circumstances) ● Same processes (psychological , linguistic) [1] Tiddi et al. (2015), An Ontology Design Pattern to Define Explanations, K-CAP2015 Determinists Hempel& Oppenheim Weber& Durkheim Charles Peirce DEFINING EXPLANATIONS (ε) V-IV AC Plato&Aristotle XVII BC 1948 19641903 2015 ?
  • 5. Explication (⋍ Interpretation) Justification Explic-/Interpret-/Explainability SOME DISAMBIGUATIONS Explanation ε of why a decision is good the degree to which an observer can understand the cause of a decision
  • 6. Which types? ● factual ε : why specific ‘everyday’ events occur ● scientific ε : generalising scientific theories ● reason ε : explaining behaviour and decision making Which processes? 1) cognitive : determining the causes (explanans) of an event (explanandum) and relating these to a particular context 2) social : transferring knowledge between explainer and explainee RESEARCH GOAL : INTELLIGENT SYSTEMS THAT CAN EXPLAIN
  • 7. Which audience? ● engineers/scientists/experts ● end-users Which characteristics? ● Transparency (traceability + verificability) ● Intelligibility + explainability Which language? ● Visual ● Written ● Spoken RESEARCH GOAL : INTELLIGENT SYSTEMS THAT CAN EXPLAIN
  • 8. Existing knowledge sources can serve as background (the “old”) knowledge to generate explanations: ● Plenty of available sources (not only RDF...) ● Connected, centralised hubs ● Multi-domain (serendipity!) APPROACH : REUSE AVAILABLE KNOWLEDGE SOURCES
  • 9. Generating explanations from the Web of Data [2] EXAMPLE : FACTUAL, WRITTEN ε [2] Tiddi. (2016), Explaining Data Patterns using Knowledge from the Web of Data, Ph.D. thesis. Demo: http://dedalo.kmi.open.ac.uk/ Why do people search for “A Song of Ice and Fire” only in certain periods?”
  • 10. Explaining behaviours and recommending self-learners using online resources [3] EXAMPLE : REASON, VISUAL ε [3] http://afel-project.eu
  • 11. Robots finding explanations for their behavior in a smart-city datahub [4] EXAMPLE : REASON, SPOKEN ε [4] http://sciroc.eu [ Shameless advert ] 1st ERL Smart CIties RObotics Challenge 16–22/09/2019 Milton Keynes,UK No need to have a robot!!!
  • 12. Explaining scenes in motion using ShapeNet [5] as background knowledge (and YOLO [6] for pre-processing) EXAMPLE : factual&reason, spoken ε [5] http://www.shapenet.org [6] https://pjreddie.com/darknet/yolo/
  • 13. Explaining neural attentions A multi-layer LSTM network to understanding NL robotic commands [8] Avoid training biases using linguistic corpora (FrameNet [7]) combined with domain-specific datasets EXAMPLE : REASON, VISUAL ε [7] https://framenet.icsi.berkeley.edu/fndrupal/ [8] Mensio et al., A Multi-layer LSTM-based Approach for Robot Command Interaction Modeling, Language and Robotics (LangRobo), IROS 2018.
  • 14. Explaining inconsistencies using an autonomous agent in a smart office [9] Monitoring Health&Safety using a SHACL-based model checking and behavioural trees Centralised data integration, processing and reasoning EXAMPLE : FACTUAL, WRITTEN ε [9] Bastianelli et al., Meet HanS, the Heath&Safety autonomous inspector, Posters&Demos track at ISWC 2018.
  • 15. Re-coding Black Mirror [10] workshops Bringing social&computer scientists together to understand the threats of their own technologies, and raise awareness on methods explainability Ethics by Design methodology MACHINE EXPLANATION NEED MACHINE ETHICS [10] https://kmitd.github.io/recoding-black-mirror/
  • 16. Databank ● Collection of meta-analyses to study human cooperation ● 3.5k work on social dilemmas ( = benefitting the others vs. self-interest) My goal ● creation of a research platform generating explanations for human cooperation (+ search facilities) ● Generalising the methodology to Life & Medical Sciences (long-term) WHAT ABOUT SCIENTIFIC EXPLANATIONS?

Editor's Notes

  1. Start by asking the question = why do we need systems In brackets because it is the same reason why humans need explainationa
  2. First question is what is intended for exp Looking at history (work done as part of my PhD = we use Eta as a symbol for “the concept of explanation”) There is not a real definition, but people have looked at it from the perspective of their own discipline (hence the color) Plato & A (connecting Forms and Facts through logos VS deducing the causes of why smtg happened ) Determinists (DesCartes, Leibniz, Newton, Huygens...) deductive process Peirce Lecture on Pragmatism (expl = deduction + induction) Carl Hempel & Oppenheim Deductive-Nomological Model / statistical model for explanation Weber & Durkheim (justifying social facts) Put myself just in case
  3. Removing some doubts, this in how I intend - but this is arguable Interepretation is often used as explanation but imo there’s smtg like a subjective aspect added People talk about just Also about ...ility (a degree of)
  4. Once we give some definitions, goal : s finding out how to design & implement systems that generate explanations (“that can explain”) A number of subquestions arise / a number of things are needed to build such systems : which types, which processes, Reason = intentional / factual-scientific = unintentional Processes = one cognitive & one social
  5. But also things like audience and language, as these can change the form the explanation is generated / expressed scientists or researchers might want traceability aas this guarantees transparency End users might prefer simple expl than complicated
  6. The approach I have been using is the reuse of external knowledge to bring And this is likely to be the main difference with XAI Today billions of heterogeneous data sources exist (stored/real-time, personal/public terminals…) We produce them , smart cities, the LOD, google just released...
  7. I am just going through some examples of how systems generating explanations … Dedalo = the system I develop during my PhD… was using the LOD (the big cloud of bubbles of the previous slide) as background knowledge to explain google trends Trends = how much a term is searched over time (10 years) We found trends with patterns (repeated peaks) and tried to explain why Explanations were presented to the user as natural language
  8. A project I was part last year We built a browser plugin to support “self learners” : visually explaining their behaviours, and recommending courses to improve You can use it too!
  9. A different example : a Project started this year to organise a robotics competition in a smart city MK was part of a big data infrastructure project (2014-2017) We built a Datahub : a large-scale infrastructure aggregating heterogeneous the city’s heterogeneous data Idea of SciRoc : robots will use the info in the datahub for their tasks, and my research was about helping robots to find explanation for their behaviors in the datahub No idea who’s going to do that now :)
  10. Work of a RA who worked with me this summer working on semantic mapping (introducing common-sense knowledge on a robots’ map) Avoid time-expensive model training ---> using YOLO for segmentation Combining ShapeNet (richly-annotated, large-scale dataset of 3D shapes) with robot sensorial info to perform object classification
  11. Another one worked on LSTM to parse spoken robotic commands Analysis of the attention layers = Semantic parsing of the small dataset is extremely biased by the little quantity of data Trying to use FrameNet to improve the model = generating explanations using FrameNet
  12. That (supposedly) goes on a monitoring UI for the secutiry to go and repair the problem
  13. One final thing Nice thing is the use of vignette
  14. If you have noticed that we were missing one type of E it is normal → I will do it here! First : the dataBank, then we try to generalise