SlideShare a Scribd company logo
1 of 36
Modular design patterns for
systems that learn and reason:
a boxology
Frank van Harmelen, Annette ten Teije (V1)
Vrije Universiteit Amsterdam
+ Michael van Bekkum, Maaike de Boer, André Meyer (V2)
TNO Netherlands
(https://arxiv.org/abs/2102.11965)
Creative Commons License
CC BY 3.0:
Allowed to copy, redistribute
remix & transform
But must attribute
1
Increasingly broad concensus in AI
(“the third wave”)
The next progress in AI will be driven by systems
that combine neural and symbolic techniques
Position papers by
Marcus, Lamb & Garcez, Darwiche, Pearl, Kautz, …
Keynotes at AAAI17, IJCAI18, IJCAI19, AAAI20,….
(“proof by authority”  )
2
So let’s compare
3
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
4
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
300.000 medical definitions
40 years of effort,
10.000 updates every years 5
“knowledge acquisition
bottle neck”
Strengths & Weaknesses
10M training images
Symbolic Connectionist
Construction Human effort Data hunger
Scalable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
4.8M training games
6
“sample inefficiency”
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
worse with
more data
worse with
less data
7
“sample inefficiency”
“combinatorial
explosion”
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
8
“black box problem”
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
quality

generality  9
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
10
Class: 793
Label: n04209133 (shower cap)
Certainty: 99.7%
“out of distribution generalisability”
Strengths & Weaknesses
Symbolic Connectionist
Construction Human effort Data hunger
Scaleable +/- +/-
Explainable + -
Generalisable Performance cliff Performance cliff
11
Can we get them
to collaborate?
12
So we started reading…
• 3 years of weekly reading group ≈ 75 papers
• 3x 8-week seminar with 15 students ≈100 papers
13
It was a mess…
Lot’s of techniques, tricks, ideas, methods, math
No structure, no guidance, no map, no theory
14
Ontology learning
Description logic learning
Hyperbolic embeddings
15
Goal 1: Can we make a reading map?
(as educators)
Goal 2: Can we make a modular theory?
(as scientists)
Inspired by Software Engineering:
a theory of re-usable patterns
(“Gang of four”)
16
Inspired by Software Engineering:
a theory of re-usable patterns
17
Inspired by Process Mining:
a theory of re-usable patterns
18
Inspired by Knowledge Engineering:
a theory of re-usable patterns
19
knowledge-
intensive
task
analytic
task
classification
synthetic
task
assessment
diagnosis
configuration
design
planning
scheduling
assignment
modelling
prediction
monitoring
design
object
class
attribute
feature
truth
value
generate
specify
match
obtain
Task types
Task templates
Plan:
make compositional patterns
by loose coupling
of elementary components
20
a “boxology”
learning
inference
Example: a classical ML system
21
+
=
Example: Inductive Logic Programming
22
parent(Mary,Vicky).
parent(Mary,Andre).
parent(Carrey,Vickey).
mother(Mary,Vicky).
mother(Mary,Andy).
father(Carrey,Vickey).
father(Carrey,Andy).
parent(X,Y) :- mother(X,Y).
parent(X,Y) :- father(X,Y)
parent(Carrey,Andy).
Symbols in, symbols out
• Inductive Logic Programming
• Probabilistic Soft Logic
• Markov Logic Networks
• ….
23
Intermezzo: Symbol or data?
24
“A classical machine learning system: ”
“What the <0.70, 1.17, 0.99, 1.07> is a Symbol?”
Istvan Berkeley, Minds & Machines, 2008.
1. a symbol must designate an object, a class or a relation in the world
(= the “interpretation” of the symbol)
2. symbols can be either atomic or complex,
(= composed of other symbols according to compositional rules
3. there must be system of operations that, when applied to a symbol,
generates new symbols, that again must have a designation.
cat
Symbolic prior (informed ML)
P(cushion|chair) >> P(flower|chair)
25
See survey of 100+ systems in Von Rueden et al, Learning, 2019
cushion
Learning intermediate abstractions
for reasoning
:- see( , 3), see( , 5), add(3,5,8).
End-to-end:
2x 784
inputs
19 outputs
AlphaGo
Learning intermediate abstractions
for learning
Neural
Back
end
Symbolic
Front
end
Example: Reinforcement learning for
spatial navigation
Faster adaptation to changes;
Better transfer learning
Explainable ML by rational
reconstruction
queen
crown
wears
29
shower
cap
Ranking hypotheses (≈ explaining why not)
queen
crown
wears
30
shower
cap
symbol
prediction
algorithm
From symbols to data and back again
Knowledge Graph completion
31
ML ML
From symbols to data and back again
Knowledge Graph completion
Rolling
Stones
Angi Beat It
Michael
Jackson
Publish_song
32
Angi
Rolling
Stones
Publish_song
From:
Predict:
ML ML
prediction
algorithm
From symbols to data and back again
Knowledge Graph completion
33
ML ML
Knowledge-based auto-ML
• Algorithmic configuration
• Hyperparameter tuning
• Selection of
training examples
34
Concluding
remarks
35
Goal 1: Create some structure
in the huge number of proposals
for combining learning and reasoning
Goal 2: Create modular architectures
Contribution:
A set of re-usable architectural patterns
for modular systems that learn and reason
Next steps:
• Formalise informal diagrams as pre/post-conditions
• Implement informal diagrams as a code library
• Generate diagrams via a grammar
(and predict unexplored patterns)
36

More Related Content

Similar to Modular design patterns for systems that learn and reason: a boxology

Kdd 2014 tutorial bringing structure to text - chi
Kdd 2014 tutorial   bringing structure to text - chiKdd 2014 tutorial   bringing structure to text - chi
Kdd 2014 tutorial bringing structure to text - chiBarbara Starr
 
AML_030607.ppt
AML_030607.pptAML_030607.ppt
AML_030607.pptbutest
 
The Role Of Ontology In Modern Expert Systems Dallas 2008
The Role Of Ontology In Modern Expert Systems   Dallas   2008The Role Of Ontology In Modern Expert Systems   Dallas   2008
The Role Of Ontology In Modern Expert Systems Dallas 2008Jason Morris
 
From Research Objects to Reproducible Science Tales
From Research Objects to Reproducible Science TalesFrom Research Objects to Reproducible Science Tales
From Research Objects to Reproducible Science TalesBertram Ludäscher
 
Chapter01 introductory handbook
Chapter01 introductory handbookChapter01 introductory handbook
Chapter01 introductory handbookRaman Kannan
 
A Few Useful Things to Know about Machine Learning
A Few Useful Things to Know about Machine LearningA Few Useful Things to Know about Machine Learning
A Few Useful Things to Know about Machine Learningnep_test_account
 
SE18_Lec 06_Object Oriented Analysis and Design
SE18_Lec 06_Object Oriented Analysis and DesignSE18_Lec 06_Object Oriented Analysis and Design
SE18_Lec 06_Object Oriented Analysis and DesignAmr E. Mohamed
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.pptbutest
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.pptbutest
 
Machine Learning: Decision Trees Chapter 18.1-18.3
Machine Learning: Decision Trees Chapter 18.1-18.3Machine Learning: Decision Trees Chapter 18.1-18.3
Machine Learning: Decision Trees Chapter 18.1-18.3butest
 
Learning
LearningLearning
Learningbutest
 
The Philosophical Aspects of Data Modelling
The Philosophical Aspects of Data ModellingThe Philosophical Aspects of Data Modelling
The Philosophical Aspects of Data ModellingEmir Muñoz
 
SE_Lec 06_Object Oriented Analysis and Design
SE_Lec 06_Object Oriented Analysis and DesignSE_Lec 06_Object Oriented Analysis and Design
SE_Lec 06_Object Oriented Analysis and DesignAmr E. Mohamed
 
Machine Learning meets DevOps
Machine Learning meets DevOpsMachine Learning meets DevOps
Machine Learning meets DevOpsPooyan Jamshidi
 
Train, explain, acclaim. Build a good model in three steps
Train, explain, acclaim.  Build a good model in three stepsTrain, explain, acclaim.  Build a good model in three steps
Train, explain, acclaim. Build a good model in three stepsPrzemek Biecek
 

Similar to Modular design patterns for systems that learn and reason: a boxology (20)

Kdd 2014 tutorial bringing structure to text - chi
Kdd 2014 tutorial   bringing structure to text - chiKdd 2014 tutorial   bringing structure to text - chi
Kdd 2014 tutorial bringing structure to text - chi
 
Kdd by Mr.Sameer Kumar Das
Kdd by Mr.Sameer Kumar DasKdd by Mr.Sameer Kumar Das
Kdd by Mr.Sameer Kumar Das
 
AML_030607.ppt
AML_030607.pptAML_030607.ppt
AML_030607.ppt
 
The Role Of Ontology In Modern Expert Systems Dallas 2008
The Role Of Ontology In Modern Expert Systems   Dallas   2008The Role Of Ontology In Modern Expert Systems   Dallas   2008
The Role Of Ontology In Modern Expert Systems Dallas 2008
 
From Research Objects to Reproducible Science Tales
From Research Objects to Reproducible Science TalesFrom Research Objects to Reproducible Science Tales
From Research Objects to Reproducible Science Tales
 
Chapter01 introductory handbook
Chapter01 introductory handbookChapter01 introductory handbook
Chapter01 introductory handbook
 
A Few Useful Things to Know about Machine Learning
A Few Useful Things to Know about Machine LearningA Few Useful Things to Know about Machine Learning
A Few Useful Things to Know about Machine Learning
 
SE18_Lec 06_Object Oriented Analysis and Design
SE18_Lec 06_Object Oriented Analysis and DesignSE18_Lec 06_Object Oriented Analysis and Design
SE18_Lec 06_Object Oriented Analysis and Design
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.ppt
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.ppt
 
Machine Learning: Decision Trees Chapter 18.1-18.3
Machine Learning: Decision Trees Chapter 18.1-18.3Machine Learning: Decision Trees Chapter 18.1-18.3
Machine Learning: Decision Trees Chapter 18.1-18.3
 
Learning
LearningLearning
Learning
 
GDSC ML-1.pptx
GDSC ML-1.pptxGDSC ML-1.pptx
GDSC ML-1.pptx
 
The Philosophical Aspects of Data Modelling
The Philosophical Aspects of Data ModellingThe Philosophical Aspects of Data Modelling
The Philosophical Aspects of Data Modelling
 
SE_Lec 06_Object Oriented Analysis and Design
SE_Lec 06_Object Oriented Analysis and DesignSE_Lec 06_Object Oriented Analysis and Design
SE_Lec 06_Object Oriented Analysis and Design
 
Machine Learning meets DevOps
Machine Learning meets DevOpsMachine Learning meets DevOps
Machine Learning meets DevOps
 
Ainsworth gilbert
Ainsworth gilbertAinsworth gilbert
Ainsworth gilbert
 
Multirepsentasi paper
Multirepsentasi paperMultirepsentasi paper
Multirepsentasi paper
 
Eric Smidth
Eric SmidthEric Smidth
Eric Smidth
 
Train, explain, acclaim. Build a good model in three steps
Train, explain, acclaim.  Build a good model in three stepsTrain, explain, acclaim.  Build a good model in three steps
Train, explain, acclaim. Build a good model in three steps
 

More from Frank van Harmelen

The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"Frank van Harmelen
 
Adoption of Knowledge Graphs, mid 2022 (incomplete)
Adoption of Knowledge Graphs, mid 2022 (incomplete)Adoption of Knowledge Graphs, mid 2022 (incomplete)
Adoption of Knowledge Graphs, mid 2022 (incomplete)Frank van Harmelen
 
Adoption of Knowledge Graphs, late 2019
Adoption of Knowledge Graphs, late 2019Adoption of Knowledge Graphs, late 2019
Adoption of Knowledge Graphs, late 2019Frank van Harmelen
 
Adoption of Knowledge Graphs, mid 2019
Adoption of Knowledge Graphs, mid 2019Adoption of Knowledge Graphs, mid 2019
Adoption of Knowledge Graphs, mid 2019Frank van Harmelen
 
The Empirical Turn in Knowledge Representation
The Empirical Turn in Knowledge RepresentationThe Empirical Turn in Knowledge Representation
The Empirical Turn in Knowledge RepresentationFrank van Harmelen
 
The end of the scientific paper as we know it (or not...)
The end of the scientific paper as we know it (or not...)The end of the scientific paper as we know it (or not...)
The end of the scientific paper as we know it (or not...)Frank van Harmelen
 
On the nature of AI, and the relation between symbolic and statistical approa...
On the nature of AI, and the relation between symbolic and statistical approa...On the nature of AI, and the relation between symbolic and statistical approa...
On the nature of AI, and the relation between symbolic and statistical approa...Frank van Harmelen
 
The end of the scientific paper as we know it (in 4 easy steps)
The end of the scientific paper as we know it (in 4 easy steps)The end of the scientific paper as we know it (in 4 easy steps)
The end of the scientific paper as we know it (in 4 easy steps)Frank van Harmelen
 
Linked Open Data for Medical Guidelines Interactions
Linked Open Data for Medical  Guidelines InteractionsLinked Open Data for Medical  Guidelines Interactions
Linked Open Data for Medical Guidelines InteractionsFrank van Harmelen
 
The Web of Data: do we actually understand what we built?
The Web of Data: do we actually understand what we built?The Web of Data: do we actually understand what we built?
The Web of Data: do we actually understand what we built?Frank van Harmelen
 
Semantic Web questions we couldn't ask 10 years ago
Semantic Web questions we couldn't ask 10 years agoSemantic Web questions we couldn't ask 10 years ago
Semantic Web questions we couldn't ask 10 years agoFrank van Harmelen
 
Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...
Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...
Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...Frank van Harmelen
 
Informatics is a natural science
Informatics is a natural scienceInformatics is a natural science
Informatics is a natural scienceFrank van Harmelen
 
How the Web can change social science research (including yours)
How the Web can change social science research (including yours)How the Web can change social science research (including yours)
How the Web can change social science research (including yours)Frank van Harmelen
 
4 Popular Fallacies about the Semantic Web
4 Popular Fallacies about the Semantic Web4 Popular Fallacies about the Semantic Web
4 Popular Fallacies about the Semantic WebFrank van Harmelen
 

More from Frank van Harmelen (20)

The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"
 
Adoption of Knowledge Graphs, mid 2022 (incomplete)
Adoption of Knowledge Graphs, mid 2022 (incomplete)Adoption of Knowledge Graphs, mid 2022 (incomplete)
Adoption of Knowledge Graphs, mid 2022 (incomplete)
 
Adoption of Knowledge Graphs, late 2019
Adoption of Knowledge Graphs, late 2019Adoption of Knowledge Graphs, late 2019
Adoption of Knowledge Graphs, late 2019
 
Adoption of Knowledge Graphs, mid 2019
Adoption of Knowledge Graphs, mid 2019Adoption of Knowledge Graphs, mid 2019
Adoption of Knowledge Graphs, mid 2019
 
Empirical Semantics
Empirical SemanticsEmpirical Semantics
Empirical Semantics
 
The Empirical Turn in Knowledge Representation
The Empirical Turn in Knowledge RepresentationThe Empirical Turn in Knowledge Representation
The Empirical Turn in Knowledge Representation
 
The end of the scientific paper as we know it (or not...)
The end of the scientific paper as we know it (or not...)The end of the scientific paper as we know it (or not...)
The end of the scientific paper as we know it (or not...)
 
On the nature of AI, and the relation between symbolic and statistical approa...
On the nature of AI, and the relation between symbolic and statistical approa...On the nature of AI, and the relation between symbolic and statistical approa...
On the nature of AI, and the relation between symbolic and statistical approa...
 
The end of the scientific paper as we know it (in 4 easy steps)
The end of the scientific paper as we know it (in 4 easy steps)The end of the scientific paper as we know it (in 4 easy steps)
The end of the scientific paper as we know it (in 4 easy steps)
 
Linked Open Data for Medical Guidelines Interactions
Linked Open Data for Medical  Guidelines InteractionsLinked Open Data for Medical  Guidelines Interactions
Linked Open Data for Medical Guidelines Interactions
 
The Web of Data: do we actually understand what we built?
The Web of Data: do we actually understand what we built?The Web of Data: do we actually understand what we built?
The Web of Data: do we actually understand what we built?
 
Semantic Web questions we couldn't ask 10 years ago
Semantic Web questions we couldn't ask 10 years agoSemantic Web questions we couldn't ask 10 years ago
Semantic Web questions we couldn't ask 10 years ago
 
Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...
Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...
Knowledge Engineering rediscovered, Towards Reasoning Patterns for the Semant...
 
Informatics is a natural science
Informatics is a natural scienceInformatics is a natural science
Informatics is a natural science
 
How the Web can change social science research (including yours)
How the Web can change social science research (including yours)How the Web can change social science research (including yours)
How the Web can change social science research (including yours)
 
4 Popular Fallacies about the Semantic Web
4 Popular Fallacies about the Semantic Web4 Popular Fallacies about the Semantic Web
4 Popular Fallacies about the Semantic Web
 
WCIT2010
WCIT2010WCIT2010
WCIT2010
 
Het slimme Web 3.0
Het slimme Web 3.0Het slimme Web 3.0
Het slimme Web 3.0
 
OWL briefing
OWL briefingOWL briefing
OWL briefing
 
RDF briefing
RDF briefingRDF briefing
RDF briefing
 

Recently uploaded

Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfSumit Kumar yadav
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bSérgio Sacani
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptxRajatChauhan518211
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...ssifa0344
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCEPRINCE C P
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )aarthirajkumar25
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
G9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptG9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptMAESTRELLAMesa2
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 

Recently uploaded (20)

Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdf
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptx
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
G9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptG9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.ppt
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 

Modular design patterns for systems that learn and reason: a boxology

  • 1. Modular design patterns for systems that learn and reason: a boxology Frank van Harmelen, Annette ten Teije (V1) Vrije Universiteit Amsterdam + Michael van Bekkum, Maaike de Boer, André Meyer (V2) TNO Netherlands (https://arxiv.org/abs/2102.11965) Creative Commons License CC BY 3.0: Allowed to copy, redistribute remix & transform But must attribute 1
  • 2. Increasingly broad concensus in AI (“the third wave”) The next progress in AI will be driven by systems that combine neural and symbolic techniques Position papers by Marcus, Lamb & Garcez, Darwiche, Pearl, Kautz, … Keynotes at AAAI17, IJCAI18, IJCAI19, AAAI20,…. (“proof by authority”  ) 2
  • 4. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff 4
  • 5. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff 300.000 medical definitions 40 years of effort, 10.000 updates every years 5 “knowledge acquisition bottle neck”
  • 6. Strengths & Weaknesses 10M training images Symbolic Connectionist Construction Human effort Data hunger Scalable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff 4.8M training games 6 “sample inefficiency”
  • 7. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff worse with more data worse with less data 7 “sample inefficiency” “combinatorial explosion”
  • 8. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff 8 “black box problem”
  • 9. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff quality  generality  9
  • 10. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff 10 Class: 793 Label: n04209133 (shower cap) Certainty: 99.7% “out of distribution generalisability”
  • 11. Strengths & Weaknesses Symbolic Connectionist Construction Human effort Data hunger Scaleable +/- +/- Explainable + - Generalisable Performance cliff Performance cliff 11
  • 12. Can we get them to collaborate? 12
  • 13. So we started reading… • 3 years of weekly reading group ≈ 75 papers • 3x 8-week seminar with 15 students ≈100 papers 13 It was a mess… Lot’s of techniques, tricks, ideas, methods, math No structure, no guidance, no map, no theory
  • 14. 14 Ontology learning Description logic learning Hyperbolic embeddings
  • 15. 15 Goal 1: Can we make a reading map? (as educators) Goal 2: Can we make a modular theory? (as scientists)
  • 16. Inspired by Software Engineering: a theory of re-usable patterns (“Gang of four”) 16
  • 17. Inspired by Software Engineering: a theory of re-usable patterns 17
  • 18. Inspired by Process Mining: a theory of re-usable patterns 18
  • 19. Inspired by Knowledge Engineering: a theory of re-usable patterns 19 knowledge- intensive task analytic task classification synthetic task assessment diagnosis configuration design planning scheduling assignment modelling prediction monitoring design object class attribute feature truth value generate specify match obtain Task types Task templates
  • 20. Plan: make compositional patterns by loose coupling of elementary components 20 a “boxology” learning inference
  • 21. Example: a classical ML system 21 + =
  • 22. Example: Inductive Logic Programming 22 parent(Mary,Vicky). parent(Mary,Andre). parent(Carrey,Vickey). mother(Mary,Vicky). mother(Mary,Andy). father(Carrey,Vickey). father(Carrey,Andy). parent(X,Y) :- mother(X,Y). parent(X,Y) :- father(X,Y) parent(Carrey,Andy).
  • 23. Symbols in, symbols out • Inductive Logic Programming • Probabilistic Soft Logic • Markov Logic Networks • …. 23
  • 24. Intermezzo: Symbol or data? 24 “A classical machine learning system: ” “What the <0.70, 1.17, 0.99, 1.07> is a Symbol?” Istvan Berkeley, Minds & Machines, 2008. 1. a symbol must designate an object, a class or a relation in the world (= the “interpretation” of the symbol) 2. symbols can be either atomic or complex, (= composed of other symbols according to compositional rules 3. there must be system of operations that, when applied to a symbol, generates new symbols, that again must have a designation. cat
  • 25. Symbolic prior (informed ML) P(cushion|chair) >> P(flower|chair) 25 See survey of 100+ systems in Von Rueden et al, Learning, 2019 cushion
  • 26. Learning intermediate abstractions for reasoning :- see( , 3), see( , 5), add(3,5,8). End-to-end: 2x 784 inputs 19 outputs AlphaGo
  • 27. Learning intermediate abstractions for learning Neural Back end Symbolic Front end
  • 28. Example: Reinforcement learning for spatial navigation Faster adaptation to changes; Better transfer learning
  • 29. Explainable ML by rational reconstruction queen crown wears 29 shower cap
  • 30. Ranking hypotheses (≈ explaining why not) queen crown wears 30 shower cap symbol
  • 31. prediction algorithm From symbols to data and back again Knowledge Graph completion 31 ML ML
  • 32. From symbols to data and back again Knowledge Graph completion Rolling Stones Angi Beat It Michael Jackson Publish_song 32 Angi Rolling Stones Publish_song From: Predict: ML ML
  • 33. prediction algorithm From symbols to data and back again Knowledge Graph completion 33 ML ML
  • 34. Knowledge-based auto-ML • Algorithmic configuration • Hyperparameter tuning • Selection of training examples 34
  • 36. Goal 1: Create some structure in the huge number of proposals for combining learning and reasoning Goal 2: Create modular architectures Contribution: A set of re-usable architectural patterns for modular systems that learn and reason Next steps: • Formalise informal diagrams as pre/post-conditions • Implement informal diagrams as a code library • Generate diagrams via a grammar (and predict unexplored patterns) 36