SlideShare a Scribd company logo
1 of 52
Download to read offline
AAAI - EDGeS
2023
Lifelong formal-modelling
agents
AAAI - EDGeS
Hyatt Regency San Francisco Airport, Burlingame, CA
March 27-29, 2023
AAAI Spring Symposium Series
Jacques (aka. Santiago) Basaldúa
AAAI - EDGeS
2023
AAAI - EDGeS
2023
1. Why code?
- Von Neumann's argument
- All models are code
- Biological inspiration
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
Von Neumann’s argument
AAAI - EDGeS
2023
1. Why code?
- Von Neumann's argument
- All models are code
- Biological inspiration
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
All models are code …
… just using the same sequence of operations on different parameters.
Is it good enough to wait for the convolutional network to learn how to multiply?
AAAI - EDGeS
2023
1. Why code?
- Von Neumann's argument
- All models are code
- Biological inspiration
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
The origin of everything
(before code)
1. Matter: Higgs mechanism, 1960-2012
2. Protons, e-
: Particle Physics, 1950-1970s
3. Atoms: Nuclear Physics, 1906-1950s
4. Molecules: Chemistry XIX (1869, Mendeleev)
5. Biomolecules: Miller-Urey, 1952
AAAI - EDGeS
2023
The origin of everything
(code)
AAAI - EDGeS
2023
The origin of everything
(after code)
Lamarck & Darwin XIX: “Theory of Evolution”,
Watson & Crick, 1953 + others: Science of Evolution
AAAI - EDGeS
2023
Possible forms of code
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
- Complexity of the search and forward running code
- Formal fields and what we cannot do with blocks
- Concepts as a step towards “language as code”
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
Macroscopic
Computer resources by the € Clock Cycles Evaluations @(1M/sec)
1 euro 4 x 1013
4 x 1010
1 million euros 4 x 1019
4 x 1016
1 billion euros 4 x 1022
4 x 1019
GDP of the whole planet 1014
(USD)
Age of the universe 1.4 x 1010
(years) 4.3 x 1017
(sec)
Weight of all biomass of the planet 5.6 x 1011
(ton) 5.6 x 1014
(Kg)
Human population
Human population 8 x 109
Doing something 1000 times (taking
pictures, buying, eating, …)
8 x 1012
Doing something a million times 8 x 1015
AAAI - EDGeS
2023
The Universe
Number of particles in the universe: 1080
AAAI - EDGeS
2023
Combinatorial
• Tic-tac-toe positions 26·103
• Chess game tree complexity 10120
• Fitting GPT3 s^(170·10⁹) (s == size of “parameter”) if there was only 1 solution
• Writing Shakespeare at random
• …
AAAI - EDGeS
2023
Formal
A(4) = 4!!!! cannot be computed on Earth
B(9) = A(A(A(A(A(A(A(A(A(9))))))))) cannot be computed using the whole
universe as a computer
C(9) = B(B(B(B(B(B(B(B(B(9))))))))) is still a finite number
AAAI - EDGeS
2023
Countable, Continuum and the
Power Set of ℝ
Countable:
0
1
2
Continuum:
Power Set of ℝ:
• The set of all integers
• The set of rational numbers
• The set of tuples of integers
. . .
• The set of all real numbers
• The set of tuples of real numbers
. . .
• The set of all sets of real numbers
• The set of functions from ℝ → ℝ
. . .
AAAI - EDGeS
2023
Forward running code
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
- Complexity of the search and forward running code
- Formal fields and what we cannot do with blocks
- Concepts as a step towards “language as code”
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
Formal fields and what we
cannot do with blocks
AAAI - EDGeS
2023
An object cannot possibly
represent a concept. At the
minimum, we need a data
structure that can dynamically
grow (e.g., a graph)
Formal fields and what we
cannot do with blocks
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
- Complexity of the search and forward running code
- Formal fields and what we cannot do with blocks
- Concepts as a step towards “language as code”
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
Concepts as a step towards
“language as code”
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
- The ARC challenge
- Speech to text using in our framework
- bAbI as our “language as code” bAbY
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
The ARC Challenge
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
- The ARC challenge
- Speech to text using in our framework
- bAbI as our “language as code” bAbY
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
Speech to text using in our framework
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
- The ARC challenge
- Speech to text using in our framework
- bAbI as our “language as code” bAbY
4. Our Vision: Purpose and Long-Term Goals
AAAI - EDGeS
2023
The primitives in this example
are: {person, location, to move
to, to be at, to be with, then,
and, they, where, who}
Using blending, abstraction
and interrogation the text runs
as code and generates the
answers.
“I assume Jabari is a person” is
a question asked by the
blender since Jabari is an
unseen word.
bAbI as our “language as code” bAbY
AAAI - EDGeS
2023
AAAI - EDGeS
2023
AAAI - EDGeS
2023
AAAI - EDGeS
2023
AAAI - EDGeS
2023
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
- We need specific definitions of intelligence and understanding
- Agency and learning
- Present and future goals
AAAI - EDGeS
2023
We need specific definitions of
intelligence and understanding
Once we use code as our knowledge representation: Understanding is
being able to successfully run and evaluate code in order to optimize it.
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
- We need specific definitions of intelligence and understanding
- Agency and learning
- Present and future goals
AAAI - EDGeS
2023
Agency and learning
Lifelong systems
exploit what they
have learned
requiring less
learning, not
more.
Most system in
production today,
don’t learn at all.
AAAI - EDGeS
2023
1. Why code?
2. Code as Knowledge Representation
3. Putting Ideas into Action: Implementations
4. Our Vision: Purpose and Long-Term Goals
- We need specific definitions of intelligence and understanding
- Agency and learning
- Present and future goals
AAAI - EDGeS
2023
Present and future goals
We need interpretable natural language
systems do to human/computer interaction.
This Not this
AAAI - EDGeS
2023
Present and future goals
AAAI - EDGeS
2023
Thank you!
ARC challenge: https://github.com/kaalam/JazzARC
Development: https://github.com/kaalam/Jazz
Programming doc: https://kaalam.github.io/develop
Jazz reference: https://kaalam.github.io/jazz_reference
Twitter: @kaalam_ai @BBVA_AIFactory
BBVA AI Factory
September, 2021
Building transformative AI products
in the banking industry
52
This is the BBVA AI Factory
Our offices
Who we are
We produce data products
We work to respond to the bank’s priorities creating
new products based on Artificial Intelligence
Multidisciplinary teams
We share our day-to-day work among data scientists, engineers, AI
architects, domain experts and other professionals
We are a fully-owned subsidiary of BBVA
BBVA AI Factory is the global development center where BBVA
builds the Artificial Intelligence capabilities

More Related Content

Similar to Lifelong Formal Modeling Agents at AAAI-EDGeS 2023.pdf

"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companiesData Science Milan
 
Performance #5 cpu and battery
Performance #5  cpu and batteryPerformance #5  cpu and battery
Performance #5 cpu and batteryVitali Pekelis
 
Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...
Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...
Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...Databricks
 
IRJET - Visual E-Commerce Application using Deep Learning
IRJET - Visual E-Commerce Application using Deep LearningIRJET - Visual E-Commerce Application using Deep Learning
IRJET - Visual E-Commerce Application using Deep LearningIRJET Journal
 
Designing Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsDesigning Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsAmélie Gyrard
 
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Workshop -  Architecting Innovative Graph Applications- GraphSummit MilanWorkshop -  Architecting Innovative Graph Applications- GraphSummit Milan
Workshop - Architecting Innovative Graph Applications- GraphSummit MilanNeo4j
 
Full-stack Web Development with MongoDB, Node.js and AWS
Full-stack Web Development with MongoDB, Node.js and AWSFull-stack Web Development with MongoDB, Node.js and AWS
Full-stack Web Development with MongoDB, Node.js and AWSMongoDB
 
How Azure helps to build better business processes and customer experiences w...
How Azure helps to build better business processes and customer experiences w...How Azure helps to build better business processes and customer experiences w...
How Azure helps to build better business processes and customer experiences w...Maxim Salnikov
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfNeo4j
 
WELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptxWELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptx9D38SHIDHANTMITTAL
 
Use Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengeht
Use Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengehtUse Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengeht
Use Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengehtHOOD Group
 
Facial Recognition Based Attendance System
Facial Recognition Based Attendance SystemFacial Recognition Based Attendance System
Facial Recognition Based Attendance SystemIRJET Journal
 
Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...
Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...
Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...Ray Février
 
EIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdf
EIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdfEIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdf
EIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdfEarley Information Science
 
Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)Neo4j
 
Tutorial helsinki 20180313 v1
Tutorial helsinki 20180313 v1Tutorial helsinki 20180313 v1
Tutorial helsinki 20180313 v1ISSIP
 
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...AgileNetwork
 
Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...
Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...
Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...DicodingEvent
 
Intel 20180608 v2
Intel 20180608 v2Intel 20180608 v2
Intel 20180608 v2ISSIP
 

Similar to Lifelong Formal Modeling Agents at AAAI-EDGeS 2023.pdf (20)

"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies
 
Performance #5 cpu and battery
Performance #5  cpu and batteryPerformance #5  cpu and battery
Performance #5 cpu and battery
 
Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...
Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...
Bringing an AI Ecosystem to the Domain Expert and Enterprise AI Developer wit...
 
IRJET - Visual E-Commerce Application using Deep Learning
IRJET - Visual E-Commerce Application using Deep LearningIRJET - Visual E-Commerce Application using Deep Learning
IRJET - Visual E-Commerce Application using Deep Learning
 
Designing Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsDesigning Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things Applications
 
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Workshop -  Architecting Innovative Graph Applications- GraphSummit MilanWorkshop -  Architecting Innovative Graph Applications- GraphSummit Milan
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
 
21AI401 AI Unit 1.pdf
21AI401 AI Unit 1.pdf21AI401 AI Unit 1.pdf
21AI401 AI Unit 1.pdf
 
Full-stack Web Development with MongoDB, Node.js and AWS
Full-stack Web Development with MongoDB, Node.js and AWSFull-stack Web Development with MongoDB, Node.js and AWS
Full-stack Web Development with MongoDB, Node.js and AWS
 
How Azure helps to build better business processes and customer experiences w...
How Azure helps to build better business processes and customer experiences w...How Azure helps to build better business processes and customer experiences w...
How Azure helps to build better business processes and customer experiences w...
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
 
WELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptxWELCOME TO AI PROJECT shidhant mittaal.pptx
WELCOME TO AI PROJECT shidhant mittaal.pptx
 
Use Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengeht
Use Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengehtUse Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengeht
Use Case 2.0- Wie etabliertes RE mit agiler Arbeitsweise wirklich zusammengeht
 
Facial Recognition Based Attendance System
Facial Recognition Based Attendance SystemFacial Recognition Based Attendance System
Facial Recognition Based Attendance System
 
Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...
Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...
Targeted Marketing: How Marketing Companies can use Big Data to Target Custom...
 
EIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdf
EIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdfEIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdf
EIS-Webinar-Silabs-KM-Content-Program-2023-06-07.pdf
 
Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)
 
Tutorial helsinki 20180313 v1
Tutorial helsinki 20180313 v1Tutorial helsinki 20180313 v1
Tutorial helsinki 20180313 v1
 
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
Agile Mumbai 2022 - Rohit Handa | Combining Human and Artificial Intelligence...
 
Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...
Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...
Memulai Karir menjadi iOS Developer - Gilang ramadhan (Academy Content Writer...
 
Intel 20180608 v2
Intel 20180608 v2Intel 20180608 v2
Intel 20180608 v2
 

Recently uploaded

Northern New England Tableau User Group (TUG) May 2024
Northern New England Tableau User Group (TUG) May 2024Northern New England Tableau User Group (TUG) May 2024
Northern New England Tableau User Group (TUG) May 2024patrickdtherriault
 
Audience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptxAudience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptxStephen266013
 
如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证
如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证
如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证a8om7o51
 
obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...
obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...
obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...yulianti213969
 
原件一样伦敦国王学院毕业证成绩单留信学历认证
原件一样伦敦国王学院毕业证成绩单留信学历认证原件一样伦敦国王学院毕业证成绩单留信学历认证
原件一样伦敦国王学院毕业证成绩单留信学历认证pwgnohujw
 
Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...
Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...
Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...Klinik Aborsi
 
Displacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second DerivativesDisplacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second Derivatives23050636
 
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样jk0tkvfv
 
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...yulianti213969
 
The Significance of Transliteration Enhancing
The Significance of Transliteration EnhancingThe Significance of Transliteration Enhancing
The Significance of Transliteration Enhancingmohamed Elzalabany
 
Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...
Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...
Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...Valters Lauzums
 
Formulas dax para power bI de microsoft.pdf
Formulas dax para power bI de microsoft.pdfFormulas dax para power bI de microsoft.pdf
Formulas dax para power bI de microsoft.pdfRobertoOcampo24
 
NOAM AAUG Adobe Summit 2024: Summit Slam Dunks
NOAM AAUG Adobe Summit 2024: Summit Slam DunksNOAM AAUG Adobe Summit 2024: Summit Slam Dunks
NOAM AAUG Adobe Summit 2024: Summit Slam Dunksgmuir1066
 
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证acoha1
 
Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...
Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...
Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...ssuserf63bd7
 
What is Insertion Sort. Its basic information
What is Insertion Sort. Its basic informationWhat is Insertion Sort. Its basic information
What is Insertion Sort. Its basic informationmuqadasqasim10
 
Bios of leading Astrologers & Researchers
Bios of leading Astrologers & ResearchersBios of leading Astrologers & Researchers
Bios of leading Astrologers & Researchersdarmandersingh4580
 
Predictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting TechniquesPredictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting TechniquesBoston Institute of Analytics
 
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarjSCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarjadimosmejiaslendon
 
Genuine love spell caster )! ,+27834335081) Ex lover back permanently in At...
Genuine love spell caster )! ,+27834335081)   Ex lover back permanently in At...Genuine love spell caster )! ,+27834335081)   Ex lover back permanently in At...
Genuine love spell caster )! ,+27834335081) Ex lover back permanently in At...BabaJohn3
 

Recently uploaded (20)

Northern New England Tableau User Group (TUG) May 2024
Northern New England Tableau User Group (TUG) May 2024Northern New England Tableau User Group (TUG) May 2024
Northern New England Tableau User Group (TUG) May 2024
 
Audience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptxAudience Researchndfhcvnfgvgbhujhgfv.pptx
Audience Researchndfhcvnfgvgbhujhgfv.pptx
 
如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证
如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证
如何办理加州大学伯克利分校毕业证(UCB毕业证)成绩单留信学历认证
 
obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...
obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...
obat aborsi Bontang wa 081336238223 jual obat aborsi cytotec asli di Bontang6...
 
原件一样伦敦国王学院毕业证成绩单留信学历认证
原件一样伦敦国王学院毕业证成绩单留信学历认证原件一样伦敦国王学院毕业证成绩单留信学历认证
原件一样伦敦国王学院毕业证成绩单留信学历认证
 
Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...
Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...
Jual Obat Aborsi Bandung (Asli No.1) Wa 082134680322 Klinik Obat Penggugur Ka...
 
Displacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second DerivativesDisplacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second Derivatives
 
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
 
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
 
The Significance of Transliteration Enhancing
The Significance of Transliteration EnhancingThe Significance of Transliteration Enhancing
The Significance of Transliteration Enhancing
 
Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...
Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...
Data Analytics for Digital Marketing Lecture for Advanced Digital & Social Me...
 
Formulas dax para power bI de microsoft.pdf
Formulas dax para power bI de microsoft.pdfFormulas dax para power bI de microsoft.pdf
Formulas dax para power bI de microsoft.pdf
 
NOAM AAUG Adobe Summit 2024: Summit Slam Dunks
NOAM AAUG Adobe Summit 2024: Summit Slam DunksNOAM AAUG Adobe Summit 2024: Summit Slam Dunks
NOAM AAUG Adobe Summit 2024: Summit Slam Dunks
 
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(WashU毕业证书)圣路易斯华盛顿大学毕业证成绩单本科硕士学位证留信学历认证
 
Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...
Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...
Statistics Informed Decisions Using Data 5th edition by Michael Sullivan solu...
 
What is Insertion Sort. Its basic information
What is Insertion Sort. Its basic informationWhat is Insertion Sort. Its basic information
What is Insertion Sort. Its basic information
 
Bios of leading Astrologers & Researchers
Bios of leading Astrologers & ResearchersBios of leading Astrologers & Researchers
Bios of leading Astrologers & Researchers
 
Predictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting TechniquesPredictive Precipitation: Advanced Rain Forecasting Techniques
Predictive Precipitation: Advanced Rain Forecasting Techniques
 
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarjSCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
SCI8-Q4-MOD11.pdfwrwujrrjfaajerjrajrrarj
 
Genuine love spell caster )! ,+27834335081) Ex lover back permanently in At...
Genuine love spell caster )! ,+27834335081)   Ex lover back permanently in At...Genuine love spell caster )! ,+27834335081)   Ex lover back permanently in At...
Genuine love spell caster )! ,+27834335081) Ex lover back permanently in At...
 

Lifelong Formal Modeling Agents at AAAI-EDGeS 2023.pdf

  • 1. AAAI - EDGeS 2023 Lifelong formal-modelling agents AAAI - EDGeS Hyatt Regency San Francisco Airport, Burlingame, CA March 27-29, 2023 AAAI Spring Symposium Series Jacques (aka. Santiago) Basaldúa
  • 3. AAAI - EDGeS 2023 1. Why code? - Von Neumann's argument - All models are code - Biological inspiration 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals
  • 4. AAAI - EDGeS 2023 Von Neumann’s argument
  • 5. AAAI - EDGeS 2023 1. Why code? - Von Neumann's argument - All models are code - Biological inspiration 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals
  • 6. AAAI - EDGeS 2023 All models are code … … just using the same sequence of operations on different parameters. Is it good enough to wait for the convolutional network to learn how to multiply?
  • 7. AAAI - EDGeS 2023 1. Why code? - Von Neumann's argument - All models are code - Biological inspiration 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals
  • 8. AAAI - EDGeS 2023 The origin of everything (before code) 1. Matter: Higgs mechanism, 1960-2012 2. Protons, e- : Particle Physics, 1950-1970s 3. Atoms: Nuclear Physics, 1906-1950s 4. Molecules: Chemistry XIX (1869, Mendeleev) 5. Biomolecules: Miller-Urey, 1952
  • 9. AAAI - EDGeS 2023 The origin of everything (code)
  • 10. AAAI - EDGeS 2023 The origin of everything (after code) Lamarck & Darwin XIX: “Theory of Evolution”, Watson & Crick, 1953 + others: Science of Evolution
  • 11. AAAI - EDGeS 2023 Possible forms of code
  • 12. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation - Complexity of the search and forward running code - Formal fields and what we cannot do with blocks - Concepts as a step towards “language as code” 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals
  • 13. AAAI - EDGeS 2023 Macroscopic Computer resources by the € Clock Cycles Evaluations @(1M/sec) 1 euro 4 x 1013 4 x 1010 1 million euros 4 x 1019 4 x 1016 1 billion euros 4 x 1022 4 x 1019 GDP of the whole planet 1014 (USD) Age of the universe 1.4 x 1010 (years) 4.3 x 1017 (sec) Weight of all biomass of the planet 5.6 x 1011 (ton) 5.6 x 1014 (Kg) Human population Human population 8 x 109 Doing something 1000 times (taking pictures, buying, eating, …) 8 x 1012 Doing something a million times 8 x 1015
  • 14. AAAI - EDGeS 2023 The Universe Number of particles in the universe: 1080
  • 15. AAAI - EDGeS 2023 Combinatorial • Tic-tac-toe positions 26·103 • Chess game tree complexity 10120 • Fitting GPT3 s^(170·10⁹) (s == size of “parameter”) if there was only 1 solution • Writing Shakespeare at random • …
  • 16. AAAI - EDGeS 2023 Formal A(4) = 4!!!! cannot be computed on Earth B(9) = A(A(A(A(A(A(A(A(A(9))))))))) cannot be computed using the whole universe as a computer C(9) = B(B(B(B(B(B(B(B(B(9))))))))) is still a finite number
  • 17. AAAI - EDGeS 2023 Countable, Continuum and the Power Set of ℝ Countable: 0 1 2 Continuum: Power Set of ℝ: • The set of all integers • The set of rational numbers • The set of tuples of integers . . . • The set of all real numbers • The set of tuples of real numbers . . . • The set of all sets of real numbers • The set of functions from ℝ → ℝ . . .
  • 19. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation - Complexity of the search and forward running code - Formal fields and what we cannot do with blocks - Concepts as a step towards “language as code” 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals
  • 20. AAAI - EDGeS 2023 Formal fields and what we cannot do with blocks
  • 21. AAAI - EDGeS 2023 An object cannot possibly represent a concept. At the minimum, we need a data structure that can dynamically grow (e.g., a graph) Formal fields and what we cannot do with blocks
  • 22. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation - Complexity of the search and forward running code - Formal fields and what we cannot do with blocks - Concepts as a step towards “language as code” 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals
  • 23. AAAI - EDGeS 2023 Concepts as a step towards “language as code”
  • 24. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations - The ARC challenge - Speech to text using in our framework - bAbI as our “language as code” bAbY 4. Our Vision: Purpose and Long-Term Goals
  • 25. AAAI - EDGeS 2023 The ARC Challenge
  • 26. AAAI - EDGeS 2023 The ARC Challenge
  • 27. AAAI - EDGeS 2023 The ARC Challenge
  • 28. AAAI - EDGeS 2023 The ARC Challenge
  • 29. AAAI - EDGeS 2023 The ARC Challenge
  • 30. AAAI - EDGeS 2023 The ARC Challenge
  • 31. AAAI - EDGeS 2023 The ARC Challenge
  • 32. AAAI - EDGeS 2023 The ARC Challenge
  • 33. AAAI - EDGeS 2023 The ARC Challenge
  • 34. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations - The ARC challenge - Speech to text using in our framework - bAbI as our “language as code” bAbY 4. Our Vision: Purpose and Long-Term Goals
  • 35. AAAI - EDGeS 2023 Speech to text using in our framework
  • 36. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations - The ARC challenge - Speech to text using in our framework - bAbI as our “language as code” bAbY 4. Our Vision: Purpose and Long-Term Goals
  • 37. AAAI - EDGeS 2023 The primitives in this example are: {person, location, to move to, to be at, to be with, then, and, they, where, who} Using blending, abstraction and interrogation the text runs as code and generates the answers. “I assume Jabari is a person” is a question asked by the blender since Jabari is an unseen word. bAbI as our “language as code” bAbY
  • 43. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals - We need specific definitions of intelligence and understanding - Agency and learning - Present and future goals
  • 44. AAAI - EDGeS 2023 We need specific definitions of intelligence and understanding Once we use code as our knowledge representation: Understanding is being able to successfully run and evaluate code in order to optimize it.
  • 45. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals - We need specific definitions of intelligence and understanding - Agency and learning - Present and future goals
  • 46. AAAI - EDGeS 2023 Agency and learning Lifelong systems exploit what they have learned requiring less learning, not more. Most system in production today, don’t learn at all.
  • 47. AAAI - EDGeS 2023 1. Why code? 2. Code as Knowledge Representation 3. Putting Ideas into Action: Implementations 4. Our Vision: Purpose and Long-Term Goals - We need specific definitions of intelligence and understanding - Agency and learning - Present and future goals
  • 48. AAAI - EDGeS 2023 Present and future goals We need interpretable natural language systems do to human/computer interaction. This Not this
  • 49. AAAI - EDGeS 2023 Present and future goals
  • 50. AAAI - EDGeS 2023 Thank you! ARC challenge: https://github.com/kaalam/JazzARC Development: https://github.com/kaalam/Jazz Programming doc: https://kaalam.github.io/develop Jazz reference: https://kaalam.github.io/jazz_reference Twitter: @kaalam_ai @BBVA_AIFactory
  • 51. BBVA AI Factory September, 2021 Building transformative AI products in the banking industry
  • 52. 52 This is the BBVA AI Factory Our offices Who we are We produce data products We work to respond to the bank’s priorities creating new products based on Artificial Intelligence Multidisciplinary teams We share our day-to-day work among data scientists, engineers, AI architects, domain experts and other professionals We are a fully-owned subsidiary of BBVA BBVA AI Factory is the global development center where BBVA builds the Artificial Intelligence capabilities