SlideShare une entreprise Scribd logo
1  sur  31
Télécharger pour lire hors ligne
OpenSherlock
Towards Open Source Hybrid Computing
People + Symbolic + Probabilistic Computing
Intelligence Augmentation
Part 1
© 2019, TopicQuests Foundation
Jack Park
Temecula Web Techies Meetup
Hosted by
American Specialty Health
Temecula, CA
5 August, 2019
Purpose and Context
• Context in Bold Claims
• Understanding many wicked
problems is like understanding
arms races
• Few people win
• The game is to find the
right questions to ask
• All stakeholders must
participate
• Scientific research means
citizens collaborating with
professionals
Solving and
Preventing
Wicked Problems
Engage Citizen Scientists Early:
AI Systems as Learning Platforms
• My daughter, Nefer, at around age 8, typed sentences into
OpenSherlock’s predecessor, TSC.
• Sentences like:
• An animal is a living thing
• A mammal is an animal
• A fish is an animal
• Her goal, at that age, was to define a taxonomy and teach
the program where she was in that taxonomy.
• The program said: “Nefer is a fish”.
• She successfully diagnosed her sentences and corrected the
taxonomy.
• At age 15, she coauthored a chapter in a Topic Maps book
about the Linnaean Taxonomy
Nefer Lin Park
Age: Very young
Douglas Engelbart:
Knowledge Gardens for All Citizens
• Douglas Engelbart believed that
• People, their Knowledge, and the
Tools they use to collaborate:
• Must co-evolve
• Must network together
• He used the term Dynamic
Knowledge Repository when
talking about that concept.
• The term Dynamic Knowledge Repository
became Knowledge Garden*
*”Knowledge Garden” suggested by Ted Kahn Diagram: Mark Szpakowski
Discovery in Context: An Example
Information Gathering in a Knowing Garden
Discovery followed by Action
Gardener
connects
concepts
Discovery followed by Action
Gardener creates new
concepts to better
explain “must avoid”
connection
Let the Conversations Begin: a Challenge
Responses Leading to New Concepts
Compromised Host is
new Concept
Gardening Outcome
antioxidants
kill
free radicals
Contraindicates
macrophages use
free radicals to
kill bacteria
Bacterial Infection Antioxidants
Because
Appropriate For
Compromised Host Co-created resource in
the garden
AI Sketches
• Distinctions
• Symbolic
• E.g. Expert Systems
• Numeric
• E.g. neural nets
• Hybrid
• Symbolic
• Numeric
• Humans in the loop
Generalized Human Capabilities
Human knowledge and
capabilities are nothing like this
curve, but it sketches the idea
that there exists some
generalized ability to remain
competent in a wide range of
topics.
These diagrams are illustrative of
certain concepts, but do not
represent any kind of reality
Generalized Expert System Capabilities
Expert Systems have been
shown to be very competent in
some topic, but brittle when
pushed to the edges of a
trained domain
Generalized Neural Net Capabilities
Recent advances in neural nets
show enormous potential in
very narrow applications
Target: Hybrid
How far, really, can we push the
envelope of humans +
computers?
A Use Case: Reading An Information Resource
• A sentence †
• The pandemic of obesity, type 2 diabetes
mellitus (T2DM) and nonalcoholic fatty
liver disease (NAFLD) has frequently been
associated with dietary intake of
saturated fats (1) and specifically with
dietary palm oil (PO) (2). This Photo by Unknown Author is licensed under CC BY-SA
† https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5272194/
AI and NLP – Machine Reading
• What is in that sentence to find
• Obesity associated with saturated fats
• Obesity associated with palm oil
• T2DM associated with saturated fats
• T2DM associated with palm oil
• NAFLD associated with saturated fats
• NAFLD associated with palm oil
Obesity associated with saturated
fats —In 3 Slides—The Predicate
{
"pred": {
"gramSize": "2",
"sentences": ["ef471f0c-08c9-4097-ac17-354a32944fe1"],
"vers": "1489448293804",
"words": "associated with",
"lexTypes": ["vp"],
"predicateTense": "present",
"id": "27637.27587",
"gramType": "pair",
"lensCodes": ["BioLens"]
},
Predicate Phrase metadatametadata
Side Note:
In OpenSherlock these
blocks of metadata are
called WordGrams
The Object
"obj": {
"dbpo": {
"@percentageOfSecondRank": "0.0",
"@URI": "http://dbpedia.org/resource/Saturated_fat",
"@support": "455",
"@surfaceForm": "saturated fats",
"@offset": "156",
"@similarityScore": "1.0",
"@types": ""
},
"gramSize": "2",
"sentences": ["ef471f0c-08c9-4097-ac17-354a32944fe1"],
"synonyms": ["27739."],
"vers": "1489448293876",
"words": "saturated fats",
"lexTypes": ["np"],
"id": "27738.13882",
"gramType": "pair"
},
DBPedia
recognized
a topic
WordNet
returned a
synonym
Object
The Subject and WordGram Triple Identity
"id": "27000._27637.27587_27738.13882T",
"subj": {
"dbpo": {
"@percentageOfSecondRank": "1.0799338377810428E-21",
"@URI": "http://dbpedia.org/resource/Obesity",
"@support": "3012",
"@surfaceForm": "obesity",
"@offset": "16",
"@similarityScore": "1.0",
"@types": "DBpedia:Disease"
},
"gramSize": "1",
"sentences": ["ef471f0c-08c9-4097-ac17-354a32944fe1"],
"vers": "1489448293875",
"words": "obesity",
"lexTypes": ["n"],
"id": "27000.",
"gramType": "singleton"
}
DBPedia
recognized
a topic
Subject
ID of this Triple
Another Use Case: Undiscovered Knowledge
• Undiscovered Knowledge
• Universe of Discourse A: Raynaud’s Syndrome
• Known Rx: Blood Thinners
• Universe of Discourse B: Fish Oil
• Known property: Blood Thinner
• The two domains of discourse do not know about each other
• A Lens on This Situation
• Information Silos
On Information Silos
• An insular management system†
• Silo effect arises from
• Silo mentality
• Incompatible data and information systems
• Domain specialization
• …
• Silo effect creates
• Reduced signal to noise ratio in public information systems
• Redundant resources
• Unconnected concepts (dots)
• ... †https://en.wikipedia.org/wiki/Information_silo
Img: Doc Searls:
https://www.flickr.com/photos/docsearls/5500714140
Silo Effect: A Complex Example
• Alzheimer’s Context†
• Dr. Trumble and the Tsimané Project‡
• Anthropologist studying evolutionary medicine
• Indigenous people, Bolivia
• Higher elderly cognitive performance with the ApoE4 gene
• Dr. Liddelow studying immune response in brains
• Some people die without dementia but with brains clogged with Alzheimer’s pathology
• A Quote (emphasis mine):
• “I asked Dr. Liddelow whether he was familiar with the Tsimane research. He admitted that he was not
— the field of evolutionary biology is distant from his own. But he said the hypothesis that the ApoE4
gene evolved to protect our brains from the effects of parasitic infection made perfect sense. “That’s
absolutely in line with what we found. For our ancestors, an ApoE4 gene could have been beneficial,”
Dr. Liddelow said, in part because it would have helped the astrocytes go on the attack.”
†
Kennedy, P. (2017, July 14). An Ancient Cure for Alzheimer's? The New York Times.
‡ University of New Mexico. The Tsimane Health and Life History Project. http://www.unm.edu/~tsimane/
Literature-based Discovery
• Using literature (documents) to
find new relations in existing
“knowledge” (discovery)
• Mitigate silo effect
• Literature-based Discovery, the
field, was created by the
information scientist Don R.
Swanson in the 1980s.†
• Does not produce new
“knowledge” as would laboratory
experiments Swanson Linking
†see Swanson, Don (1988). "Migraine and Magnesium: Eleven Neglected
Connections". Perspectives in Biology and Medicine. 31 (4): 526–557.
Find Intermediate literature B
which links topic A with topic C
Swanson’s ABC Linking Method†
1. Pick a topic of interest (Raynaud’s Disease)
2. Search to find literature A = {Raynaud’s}
3. Hypothesize that B (e.g., blood factors) should be studied in relation to
Raynaud’s
4. Search literature A’ = A ∩ {blood}
5. Notice two common descriptors: blood viscosity, red blood cell rigidity
6. Search literature C = {blood viscosity} U { red blood cell rigidity }
7. Notice the term “Fish Oil”
8. Search literature C = {Fish Oil}
9. Show {Fish Oil} ∩ {Raynaud’s} = { }
10. Show plausible connection between Raynaud’s and Fish Oil
Show the literature has not yet made
the connection (empty set)
†Adapted from: http://www.dimacs.rutgers.edu/~billp/pubs/JASISTLBD.pdf
Let’s Revisit the Reynaud’s Example
Photo by Michal Vrba on Unsplash
Machine Reading In the Two Silos
• Silo A • Silo B • Machine Reading collects
graph structures from
different sources
• Form tuple-like structures
which are graphs
Ways to Federate those Silos?
Photo by You X Ventures on Unsplash
Machine Reading: Topic Mapping
• TopicMap Process
• Rule:
• One Location in the Map for each
Subject
• Federates (merges topics about
the same subject) collected from
different resources
• Federation does a Union on
topics from disparate sources
• Federation Intersects silos
around common topics
• Topic Map
Federation Opens Questions
• Can Fish Oil be a Raynaud’s Rx?
• Turns out: Yes?
Photo by Johannes Plenio on Unsplash
Next Time:
OpenSherlock Architecture

Contenu connexe

Similaire à OpenSherlock - Hybrid Computing - Intelligence Augmentation

John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...
John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...
John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...SeriousGamesAssoc
 
Overview Write a 2–3-page assessment in which you respond to a ser.docx
Overview Write a 2–3-page assessment in which you respond to a ser.docxOverview Write a 2–3-page assessment in which you respond to a ser.docx
Overview Write a 2–3-page assessment in which you respond to a ser.docxkarlacauq0
 
Biol161 01
Biol161 01Biol161 01
Biol161 01gfb1
 
Angrist Fogm vi_7march2013
Angrist Fogm vi_7march2013Angrist Fogm vi_7march2013
Angrist Fogm vi_7march2013Misha Angrist
 
Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)Kieran Ryan
 
Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)Kieran Ryan
 
1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 final1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 finalamgonzalezpineiro
 
Creative Writing Workshop
Creative Writing WorkshopCreative Writing Workshop
Creative Writing WorkshopCamille Ruiz
 
Creative Writing
Creative WritingCreative Writing
Creative Writing12hector
 
1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 final1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 finalNicole Rivera
 
1. creative writing workshop april 2015 final (1)
1. creative writing workshop april 2015 final (1)1. creative writing workshop april 2015 final (1)
1. creative writing workshop april 2015 final (1)ramoncolon7
 
Creative writing workshop april 2015
Creative writing workshop april 2015 Creative writing workshop april 2015
Creative writing workshop april 2015 Carolina Ayala
 
Why life is so complicated
Why life is so complicatedWhy life is so complicated
Why life is so complicatedAnita de Waard
 
Malina bunb manizales 2015
Malina bunb manizales  2015Malina bunb manizales  2015
Malina bunb manizales 2015roger malina
 
Evolution, Humanity and Religion Where is the evidence for God?
Evolution, Humanity and Religion Where is the evidence for God?Evolution, Humanity and Religion Where is the evidence for God?
Evolution, Humanity and Religion Where is the evidence for God?William Hall
 
Kerry Blanchard Shanghai Biof
Kerry Blanchard Shanghai BiofKerry Blanchard Shanghai Biof
Kerry Blanchard Shanghai BiofSage Base
 
Explaining Essay Topics
Explaining Essay TopicsExplaining Essay Topics
Explaining Essay TopicsHeather White
 
Evolutionary arguments in medical genomics
Evolutionary arguments in medical genomicsEvolutionary arguments in medical genomics
Evolutionary arguments in medical genomicsNikita Khromov-Borisov
 
Moving From Small Science To Big Science
Moving From Small Science To Big ScienceMoving From Small Science To Big Science
Moving From Small Science To Big ScienceWebometrics Class
 

Similaire à OpenSherlock - Hybrid Computing - Intelligence Augmentation (20)

John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...
John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...
John A. Pollock - How People Learn: Stories from Transmedia for STEM and Heal...
 
Scientific writing.pptx
Scientific writing.pptxScientific writing.pptx
Scientific writing.pptx
 
Overview Write a 2–3-page assessment in which you respond to a ser.docx
Overview Write a 2–3-page assessment in which you respond to a ser.docxOverview Write a 2–3-page assessment in which you respond to a ser.docx
Overview Write a 2–3-page assessment in which you respond to a ser.docx
 
Biol161 01
Biol161 01Biol161 01
Biol161 01
 
Angrist Fogm vi_7march2013
Angrist Fogm vi_7march2013Angrist Fogm vi_7march2013
Angrist Fogm vi_7march2013
 
Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)
 
Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)Essential human sciences in 2 lessons (with extension if required)
Essential human sciences in 2 lessons (with extension if required)
 
1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 final1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 final
 
Creative Writing Workshop
Creative Writing WorkshopCreative Writing Workshop
Creative Writing Workshop
 
Creative Writing
Creative WritingCreative Writing
Creative Writing
 
1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 final1. creative writing workshop april 2015 final
1. creative writing workshop april 2015 final
 
1. creative writing workshop april 2015 final (1)
1. creative writing workshop april 2015 final (1)1. creative writing workshop april 2015 final (1)
1. creative writing workshop april 2015 final (1)
 
Creative writing workshop april 2015
Creative writing workshop april 2015 Creative writing workshop april 2015
Creative writing workshop april 2015
 
Why life is so complicated
Why life is so complicatedWhy life is so complicated
Why life is so complicated
 
Malina bunb manizales 2015
Malina bunb manizales  2015Malina bunb manizales  2015
Malina bunb manizales 2015
 
Evolution, Humanity and Religion Where is the evidence for God?
Evolution, Humanity and Religion Where is the evidence for God?Evolution, Humanity and Religion Where is the evidence for God?
Evolution, Humanity and Religion Where is the evidence for God?
 
Kerry Blanchard Shanghai Biof
Kerry Blanchard Shanghai BiofKerry Blanchard Shanghai Biof
Kerry Blanchard Shanghai Biof
 
Explaining Essay Topics
Explaining Essay TopicsExplaining Essay Topics
Explaining Essay Topics
 
Evolutionary arguments in medical genomics
Evolutionary arguments in medical genomicsEvolutionary arguments in medical genomics
Evolutionary arguments in medical genomics
 
Moving From Small Science To Big Science
Moving From Small Science To Big ScienceMoving From Small Science To Big Science
Moving From Small Science To Big Science
 

Plus de Jack Park

Topic Maps: Romancing Conversation Topics
Topic Maps: Romancing Conversation TopicsTopic Maps: Romancing Conversation Topics
Topic Maps: Romancing Conversation TopicsJack Park
 
Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview
Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview
Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview Jack Park
 
Game-based Learning Landscape and Opportunities
Game-based Learning Landscape and OpportunitiesGame-based Learning Landscape and Opportunities
Game-based Learning Landscape and OpportunitiesJack Park
 
Finding Meaning Across Boundaries
Finding Meaning Across BoundariesFinding Meaning Across Boundaries
Finding Meaning Across BoundariesJack Park
 
On Augmenting Patients
On Augmenting PatientsOn Augmenting Patients
On Augmenting PatientsJack Park
 
Open Source Cognitive Computing: Progress and Prospects
Open Source Cognitive Computing: Progress and ProspectsOpen Source Cognitive Computing: Progress and Prospects
Open Source Cognitive Computing: Progress and ProspectsJack Park
 
Knowledge Garden Overview
Knowledge Garden OverviewKnowledge Garden Overview
Knowledge Garden OverviewJack Park
 
Literature-based discovery: it's all about connecting dots in widely disparat...
Literature-based discovery: it's all about connecting dots in widely disparat...Literature-based discovery: it's all about connecting dots in widely disparat...
Literature-based discovery: it's all about connecting dots in widely disparat...Jack Park
 
Questing in the age of Complex Systems
Questing in the age of Complex SystemsQuesting in the age of Complex Systems
Questing in the age of Complex SystemsJack Park
 
FutureOfText2015
FutureOfText2015FutureOfText2015
FutureOfText2015Jack Park
 
Federating Cultures: Human Knowledge, Teachers, Students
Federating Cultures: Human Knowledge, Teachers, StudentsFederating Cultures: Human Knowledge, Teachers, Students
Federating Cultures: Human Knowledge, Teachers, StudentsJack Park
 
Towards an EarthMoonshot with Cognitive Computing
Towards an EarthMoonshot with Cognitive ComputingTowards an EarthMoonshot with Cognitive Computing
Towards an EarthMoonshot with Cognitive ComputingJack Park
 
HyperMembrane Structures for Open Source Cognitive Computing
HyperMembrane Structures for Open Source Cognitive ComputingHyperMembrane Structures for Open Source Cognitive Computing
HyperMembrane Structures for Open Source Cognitive ComputingJack Park
 
Towards An Improvement Community Platform for Service Innovation
Towards An Improvement Community Platform for Service InnovationTowards An Improvement Community Platform for Service Innovation
Towards An Improvement Community Platform for Service InnovationJack Park
 
SolrSherlock: Linkfinding among Biomolecules with Literature-based Discovery
SolrSherlock: Linkfinding among Biomolecules with Literature-based DiscoverySolrSherlock: Linkfinding among Biomolecules with Literature-based Discovery
SolrSherlock: Linkfinding among Biomolecules with Literature-based DiscoveryJack Park
 
Towards Cognitive Agents for BigData Discovery
Towards Cognitive Agents for BigData DiscoveryTowards Cognitive Agents for BigData Discovery
Towards Cognitive Agents for BigData DiscoveryJack Park
 
Feedback Loops and Knowledge Gardens
Feedback Loops and Knowledge GardensFeedback Loops and Knowledge Gardens
Feedback Loops and Knowledge GardensJack Park
 

Plus de Jack Park (20)

Tm keynote
Tm keynoteTm keynote
Tm keynote
 
Topic Maps: Romancing Conversation Topics
Topic Maps: Romancing Conversation TopicsTopic Maps: Romancing Conversation Topics
Topic Maps: Romancing Conversation Topics
 
Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview
Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview
Augmented Claim Craft Ecosystem: HyperKnowledge- OpenSherlock Overview
 
Game-based Learning Landscape and Opportunities
Game-based Learning Landscape and OpportunitiesGame-based Learning Landscape and Opportunities
Game-based Learning Landscape and Opportunities
 
Finding Meaning Across Boundaries
Finding Meaning Across BoundariesFinding Meaning Across Boundaries
Finding Meaning Across Boundaries
 
On Augmenting Patients
On Augmenting PatientsOn Augmenting Patients
On Augmenting Patients
 
Lbd tm-2
Lbd tm-2Lbd tm-2
Lbd tm-2
 
Open Source Cognitive Computing: Progress and Prospects
Open Source Cognitive Computing: Progress and ProspectsOpen Source Cognitive Computing: Progress and Prospects
Open Source Cognitive Computing: Progress and Prospects
 
Knowledge Garden Overview
Knowledge Garden OverviewKnowledge Garden Overview
Knowledge Garden Overview
 
Literature-based discovery: it's all about connecting dots in widely disparat...
Literature-based discovery: it's all about connecting dots in widely disparat...Literature-based discovery: it's all about connecting dots in widely disparat...
Literature-based discovery: it's all about connecting dots in widely disparat...
 
Questing in the age of Complex Systems
Questing in the age of Complex SystemsQuesting in the age of Complex Systems
Questing in the age of Complex Systems
 
Why?
Why?Why?
Why?
 
FutureOfText2015
FutureOfText2015FutureOfText2015
FutureOfText2015
 
Federating Cultures: Human Knowledge, Teachers, Students
Federating Cultures: Human Knowledge, Teachers, StudentsFederating Cultures: Human Knowledge, Teachers, Students
Federating Cultures: Human Knowledge, Teachers, Students
 
Towards an EarthMoonshot with Cognitive Computing
Towards an EarthMoonshot with Cognitive ComputingTowards an EarthMoonshot with Cognitive Computing
Towards an EarthMoonshot with Cognitive Computing
 
HyperMembrane Structures for Open Source Cognitive Computing
HyperMembrane Structures for Open Source Cognitive ComputingHyperMembrane Structures for Open Source Cognitive Computing
HyperMembrane Structures for Open Source Cognitive Computing
 
Towards An Improvement Community Platform for Service Innovation
Towards An Improvement Community Platform for Service InnovationTowards An Improvement Community Platform for Service Innovation
Towards An Improvement Community Platform for Service Innovation
 
SolrSherlock: Linkfinding among Biomolecules with Literature-based Discovery
SolrSherlock: Linkfinding among Biomolecules with Literature-based DiscoverySolrSherlock: Linkfinding among Biomolecules with Literature-based Discovery
SolrSherlock: Linkfinding among Biomolecules with Literature-based Discovery
 
Towards Cognitive Agents for BigData Discovery
Towards Cognitive Agents for BigData DiscoveryTowards Cognitive Agents for BigData Discovery
Towards Cognitive Agents for BigData Discovery
 
Feedback Loops and Knowledge Gardens
Feedback Loops and Knowledge GardensFeedback Loops and Knowledge Gardens
Feedback Loops and Knowledge Gardens
 

Dernier

Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company OdishaBalasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odishasmiwainfosol
 
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...OnePlan Solutions
 
Machine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringMachine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringHironori Washizaki
 
Comparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfComparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfDrew Moseley
 
MYjobs Presentation Django-based project
MYjobs Presentation Django-based projectMYjobs Presentation Django-based project
MYjobs Presentation Django-based projectAnoyGreter
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsSafe Software
 
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Natan Silnitsky
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...confluent
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureDinusha Kumarasiri
 
What is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWhat is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWave PLM
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Cizo Technology Services
 
SensoDat: Simulation-based Sensor Dataset of Self-driving Cars
SensoDat: Simulation-based Sensor Dataset of Self-driving CarsSensoDat: Simulation-based Sensor Dataset of Self-driving Cars
SensoDat: Simulation-based Sensor Dataset of Self-driving CarsChristian Birchler
 
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdfExploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdfkalichargn70th171
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalLionel Briand
 
Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Velvetech LLC
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Mater
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtimeandrehoraa
 
Introduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdfIntroduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdfFerryKemperman
 

Dernier (20)

Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company OdishaBalasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
 
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
 
Machine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their EngineeringMachine Learning Software Engineering Patterns and Their Engineering
Machine Learning Software Engineering Patterns and Their Engineering
 
Comparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdfComparing Linux OS Image Update Models - EOSS 2024.pdf
Comparing Linux OS Image Update Models - EOSS 2024.pdf
 
MYjobs Presentation Django-based project
MYjobs Presentation Django-based projectMYjobs Presentation Django-based project
MYjobs Presentation Django-based project
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data Streams
 
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
 
Odoo Development Company in India | Devintelle Consulting Service
Odoo Development Company in India | Devintelle Consulting ServiceOdoo Development Company in India | Devintelle Consulting Service
Odoo Development Company in India | Devintelle Consulting Service
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with Azure
 
What is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWhat is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need It
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
 
SensoDat: Simulation-based Sensor Dataset of Self-driving Cars
SensoDat: Simulation-based Sensor Dataset of Self-driving CarsSensoDat: Simulation-based Sensor Dataset of Self-driving Cars
SensoDat: Simulation-based Sensor Dataset of Self-driving Cars
 
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdfExploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
Exploring Selenium_Appium Frameworks for Seamless Integration with HeadSpin.pdf
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive Goal
 
2.pdf Ejercicios de programación competitiva
2.pdf Ejercicios de programación competitiva2.pdf Ejercicios de programación competitiva
2.pdf Ejercicios de programación competitiva
 
Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtime
 
Introduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdfIntroduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdf
 

OpenSherlock - Hybrid Computing - Intelligence Augmentation

  • 1. OpenSherlock Towards Open Source Hybrid Computing People + Symbolic + Probabilistic Computing Intelligence Augmentation Part 1 © 2019, TopicQuests Foundation Jack Park Temecula Web Techies Meetup Hosted by American Specialty Health Temecula, CA 5 August, 2019
  • 2. Purpose and Context • Context in Bold Claims • Understanding many wicked problems is like understanding arms races • Few people win • The game is to find the right questions to ask • All stakeholders must participate • Scientific research means citizens collaborating with professionals Solving and Preventing Wicked Problems
  • 3. Engage Citizen Scientists Early: AI Systems as Learning Platforms • My daughter, Nefer, at around age 8, typed sentences into OpenSherlock’s predecessor, TSC. • Sentences like: • An animal is a living thing • A mammal is an animal • A fish is an animal • Her goal, at that age, was to define a taxonomy and teach the program where she was in that taxonomy. • The program said: “Nefer is a fish”. • She successfully diagnosed her sentences and corrected the taxonomy. • At age 15, she coauthored a chapter in a Topic Maps book about the Linnaean Taxonomy Nefer Lin Park Age: Very young
  • 4. Douglas Engelbart: Knowledge Gardens for All Citizens • Douglas Engelbart believed that • People, their Knowledge, and the Tools they use to collaborate: • Must co-evolve • Must network together • He used the term Dynamic Knowledge Repository when talking about that concept. • The term Dynamic Knowledge Repository became Knowledge Garden* *”Knowledge Garden” suggested by Ted Kahn Diagram: Mark Szpakowski
  • 5. Discovery in Context: An Example Information Gathering in a Knowing Garden
  • 6. Discovery followed by Action Gardener connects concepts
  • 7. Discovery followed by Action Gardener creates new concepts to better explain “must avoid” connection
  • 8. Let the Conversations Begin: a Challenge
  • 9. Responses Leading to New Concepts Compromised Host is new Concept
  • 10. Gardening Outcome antioxidants kill free radicals Contraindicates macrophages use free radicals to kill bacteria Bacterial Infection Antioxidants Because Appropriate For Compromised Host Co-created resource in the garden
  • 11. AI Sketches • Distinctions • Symbolic • E.g. Expert Systems • Numeric • E.g. neural nets • Hybrid • Symbolic • Numeric • Humans in the loop
  • 12. Generalized Human Capabilities Human knowledge and capabilities are nothing like this curve, but it sketches the idea that there exists some generalized ability to remain competent in a wide range of topics. These diagrams are illustrative of certain concepts, but do not represent any kind of reality
  • 13. Generalized Expert System Capabilities Expert Systems have been shown to be very competent in some topic, but brittle when pushed to the edges of a trained domain
  • 14. Generalized Neural Net Capabilities Recent advances in neural nets show enormous potential in very narrow applications
  • 15. Target: Hybrid How far, really, can we push the envelope of humans + computers?
  • 16. A Use Case: Reading An Information Resource • A sentence † • The pandemic of obesity, type 2 diabetes mellitus (T2DM) and nonalcoholic fatty liver disease (NAFLD) has frequently been associated with dietary intake of saturated fats (1) and specifically with dietary palm oil (PO) (2). This Photo by Unknown Author is licensed under CC BY-SA † https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5272194/
  • 17. AI and NLP – Machine Reading • What is in that sentence to find • Obesity associated with saturated fats • Obesity associated with palm oil • T2DM associated with saturated fats • T2DM associated with palm oil • NAFLD associated with saturated fats • NAFLD associated with palm oil
  • 18. Obesity associated with saturated fats —In 3 Slides—The Predicate { "pred": { "gramSize": "2", "sentences": ["ef471f0c-08c9-4097-ac17-354a32944fe1"], "vers": "1489448293804", "words": "associated with", "lexTypes": ["vp"], "predicateTense": "present", "id": "27637.27587", "gramType": "pair", "lensCodes": ["BioLens"] }, Predicate Phrase metadatametadata Side Note: In OpenSherlock these blocks of metadata are called WordGrams
  • 19. The Object "obj": { "dbpo": { "@percentageOfSecondRank": "0.0", "@URI": "http://dbpedia.org/resource/Saturated_fat", "@support": "455", "@surfaceForm": "saturated fats", "@offset": "156", "@similarityScore": "1.0", "@types": "" }, "gramSize": "2", "sentences": ["ef471f0c-08c9-4097-ac17-354a32944fe1"], "synonyms": ["27739."], "vers": "1489448293876", "words": "saturated fats", "lexTypes": ["np"], "id": "27738.13882", "gramType": "pair" }, DBPedia recognized a topic WordNet returned a synonym Object
  • 20. The Subject and WordGram Triple Identity "id": "27000._27637.27587_27738.13882T", "subj": { "dbpo": { "@percentageOfSecondRank": "1.0799338377810428E-21", "@URI": "http://dbpedia.org/resource/Obesity", "@support": "3012", "@surfaceForm": "obesity", "@offset": "16", "@similarityScore": "1.0", "@types": "DBpedia:Disease" }, "gramSize": "1", "sentences": ["ef471f0c-08c9-4097-ac17-354a32944fe1"], "vers": "1489448293875", "words": "obesity", "lexTypes": ["n"], "id": "27000.", "gramType": "singleton" } DBPedia recognized a topic Subject ID of this Triple
  • 21. Another Use Case: Undiscovered Knowledge • Undiscovered Knowledge • Universe of Discourse A: Raynaud’s Syndrome • Known Rx: Blood Thinners • Universe of Discourse B: Fish Oil • Known property: Blood Thinner • The two domains of discourse do not know about each other • A Lens on This Situation • Information Silos
  • 22. On Information Silos • An insular management system† • Silo effect arises from • Silo mentality • Incompatible data and information systems • Domain specialization • … • Silo effect creates • Reduced signal to noise ratio in public information systems • Redundant resources • Unconnected concepts (dots) • ... †https://en.wikipedia.org/wiki/Information_silo Img: Doc Searls: https://www.flickr.com/photos/docsearls/5500714140
  • 23. Silo Effect: A Complex Example • Alzheimer’s Context† • Dr. Trumble and the Tsimané Project‡ • Anthropologist studying evolutionary medicine • Indigenous people, Bolivia • Higher elderly cognitive performance with the ApoE4 gene • Dr. Liddelow studying immune response in brains • Some people die without dementia but with brains clogged with Alzheimer’s pathology • A Quote (emphasis mine): • “I asked Dr. Liddelow whether he was familiar with the Tsimane research. He admitted that he was not — the field of evolutionary biology is distant from his own. But he said the hypothesis that the ApoE4 gene evolved to protect our brains from the effects of parasitic infection made perfect sense. “That’s absolutely in line with what we found. For our ancestors, an ApoE4 gene could have been beneficial,” Dr. Liddelow said, in part because it would have helped the astrocytes go on the attack.” † Kennedy, P. (2017, July 14). An Ancient Cure for Alzheimer's? The New York Times. ‡ University of New Mexico. The Tsimane Health and Life History Project. http://www.unm.edu/~tsimane/
  • 24. Literature-based Discovery • Using literature (documents) to find new relations in existing “knowledge” (discovery) • Mitigate silo effect • Literature-based Discovery, the field, was created by the information scientist Don R. Swanson in the 1980s.† • Does not produce new “knowledge” as would laboratory experiments Swanson Linking †see Swanson, Don (1988). "Migraine and Magnesium: Eleven Neglected Connections". Perspectives in Biology and Medicine. 31 (4): 526–557. Find Intermediate literature B which links topic A with topic C
  • 25. Swanson’s ABC Linking Method† 1. Pick a topic of interest (Raynaud’s Disease) 2. Search to find literature A = {Raynaud’s} 3. Hypothesize that B (e.g., blood factors) should be studied in relation to Raynaud’s 4. Search literature A’ = A ∩ {blood} 5. Notice two common descriptors: blood viscosity, red blood cell rigidity 6. Search literature C = {blood viscosity} U { red blood cell rigidity } 7. Notice the term “Fish Oil” 8. Search literature C = {Fish Oil} 9. Show {Fish Oil} ∩ {Raynaud’s} = { } 10. Show plausible connection between Raynaud’s and Fish Oil Show the literature has not yet made the connection (empty set) †Adapted from: http://www.dimacs.rutgers.edu/~billp/pubs/JASISTLBD.pdf
  • 26. Let’s Revisit the Reynaud’s Example Photo by Michal Vrba on Unsplash
  • 27. Machine Reading In the Two Silos • Silo A • Silo B • Machine Reading collects graph structures from different sources • Form tuple-like structures which are graphs
  • 28. Ways to Federate those Silos? Photo by You X Ventures on Unsplash
  • 29. Machine Reading: Topic Mapping • TopicMap Process • Rule: • One Location in the Map for each Subject • Federates (merges topics about the same subject) collected from different resources • Federation does a Union on topics from disparate sources • Federation Intersects silos around common topics • Topic Map
  • 30. Federation Opens Questions • Can Fish Oil be a Raynaud’s Rx? • Turns out: Yes?
  • 31. Photo by Johannes Plenio on Unsplash Next Time: OpenSherlock Architecture