autocatalytic endogenous reflective architecture
play

Autocatalytic Endogenous Reflective Architecture Kristinn R. - PowerPoint PPT Presentation

Dec 11, 2022 •219 likes •1.12k views

Autocatalytic Endogenous Reflective Architecture Kristinn R. Thrisson Associate Professor, School of Computer Science, Reykjavik University Member, Center for Analysis and Design of Intelligent Agents, Reykjavik U. Managing Director,

  1. Autocatalytic Endogenous Reflective Architecture Kristinn R. Thórisson Associate Professor, School of Computer Science, Reykjavik University Member, Center for Analysis and Design of Intelligent Agents, Reykjavik U. Managing Director, Icelandic Institute for Intelligent Machines, Reykjavik, Iceland www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  2. AGI Systems should be able to: - learn to be able to perform a host of unanticipated vastly different tasks - adapt to vastly new circumstances - actively acquire new knowledge for the above, as needed, of their own accord 2

  3. These Systems should be able to: - learn to be able to perform a host of unanticipated vastly different tasks - adapt to vastly new circumstances - actively acquire new knowledge for the above, as needed, of their own accord 3

  4. These Systems should be able to: - learn to be able to perform a host of unanticipated vastly different tasks - adapt to vastly new circumstances - actively acquire new knowledge for the above, as needed, of their own accord 4

  5. These Systems should be able to: - learn to be able to perform a host of unanticipated vastly different tasks - adapt to vastly new circumstances - actively acquire new knowledge for the above, as needed, of their own accord 5

  6. These Systems should be able to: - learn to be able to perform a host of unanticipated vastly different tasks - adapt to vastly new circumstances - actively acquire new knowledge for the above, as needed, of their own accord 6

  7. These Systems should be able to: - learn to be able to perform a host of unanticipated vastly different tasks - adapt to vastly new circumstances - actively acquire new knowledge for the above, as needed, of their own accord 7

  8. What AGIs Need: • Powerful adaptation mechanisms • require: Cognitive growth capabilities • which calls for: Self-inspection capabilities • which requires: a semantically and operationally closed programming language www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  9. Self-Programming: The Key to Cognitive Growth • If a system could inspect its own operation, it could possibly use experience to find better ways to operate • i.e. improve its own operation in light of acquired experience • But this would mean: architecture and algorithms must be manipulatable by the system itself • This calls for reflection : the ability of the system to self-inspect www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  10. Why is Self-Programming Needed? • Cogni&ve growth = most powerful path to achieve adapta&on • Self-programming: a way to achieve cogni&ve growth, and hence autonomy • Reduces or eliminates human control and interven&on • Less opera&onal cost • Highly autonomous systems more reusable • Building learning, flexible, self-adap&ve systems that can operate without complete pre-specifica&on of tasks • Adapta&on must be “allways on” in AGIs www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  11. What Programming Language? • All present programming languages designed to be used by human-level intelligences → Current programming paradigms cannot support cognitive development in artificial systems www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  12. Autocatalytic Endogeneous Reflective Architecture Autocatalytic Operation exclusively event-driven Attention (resource control), learning, and planning catalyze each other Operation is model-based: chains of models invoking models control the events in the system www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  13. Autocatalytic Endogeneous Reflective Architecture Endogenous All knowledge generated from a tiny seed All sub-goals auto-generated from top-level goal (provided in seed) All knowledge acquisition driven endogenously (but does not preclude exogeneous knowledge provision) www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  14. Autocatalytic Endogeneous Reflective Architecture Reflective Explicit traces of system operation allows building models of it The system’s code is parsable and readable by the system due to special programming language (Replicode) Models of self-operation enables self- control (aka meta-control). www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  15. Methodology 15

  16. Constructivist Methodology Con - struct - ivist A.I. : Self-constructive artificial intelligence systems with general knowledge acquisition skills; systems develop from a seed specification; capable of learning to perceive and act in a wide range of novel tasks, situations, and domains 16

  17. HUMANOBS Project • AERA : Broad-scope AGI-aspiring architecture • general-purpose learning in dynamic worlds domain independence • Demonstrating transversal cognitive skills • at multiple levels of granularity and abstraction • system-wide learning • temporal grounding • observation and imitation of complex realtime events • attention • inference, abstraction ... and more www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  18. A New Kind of A.I. Acquires knowledge autonomously starting with observation honed through abduction and induction Self-modeling inherent in system operation Continuous learning Domain-independent learning www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  19. (Operating System)

  20. Programming Language (Operating System)

  21. Replicode Programming Language (Operating System)

  22. Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  23. Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  24. ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  25. Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  26. Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  27. reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  28. Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  29. Cognitive Architecture Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  30. AERA Cognitive Architecture Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  31. Auto-catalytic, Endogenous, Reflective Architecture AERA Cognitive Architecture Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  32. Methodology Auto-catalytic, Endogenous, Reflective Architecture AERA Cognitive Architecture Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  33. constructivist AI Methodology Auto-catalytic, Endogenous, Reflective Architecture AERA Cognitive Architecture Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  34. Inspired by Piaget’s theory of cognitive development constructivist AI Methodology Auto-catalytic, Endogenous, Reflective Architecture AERA Cognitive Architecture Seed-Based Coding reflective Programming Paradigm Abduction + Induction + Deduction ampliative Reasoning & Logic Self-Reflection + Self-Organization Replicode Programming Language (Operating System)

  35. AERA www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

  36. AERA www.ru.is Advanced Topics in Artificial Intelligence | Reykjavik University | April 2016

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

LN-14 From pin factory to endogenous growth II. Tracing the roots of endogenous growth theory.

LN-14 From pin factory to endogenous growth II. Tracing the roots of endogenous growth theory.

LN-14 From pin factory to endogenous growth II. Tracing the roots of endogenous growth theory. Introduction We started in the previous lecture with Paul Romers article Endogenous technological change (JPE 1990) which established the concept of

136 views • 11 slides
Software Components with Fractal: Reflective Software Architecture and Runtime Reconfiguration

Software Components with Fractal: Reflective Software Architecture and Runtime Reconfiguration

Software Components with Fractal: Reflective Software Architecture and Runtime Reconfiguration Martin Monperrus Creative Commons Attribution License Copying and modifying are authorized as long as proper credit is given to the author.

907 views • 35 slides
1. Autocatalytic chemical reactions in the flow reactor 2. Replication, mutation, selection and

1. Autocatalytic chemical reactions in the flow reactor 2. Replication, mutation, selection and

1. Autocatalytic chemical reactions in the flow reactor 2. Replication, mutation, selection and Shannon information 3. Evolution in silico and optimization of RNA structures 4. Random walks and ensemble learning 5. Sequence-structure

1.34k views • 94 slides
Endogenous Technological Change October 2007 () Endogenous Techological Change October 2007 1

Endogenous Technological Change October 2007 () Endogenous Techological Change October 2007 1

Endogenous Technological Change October 2007 () Endogenous Techological Change October 2007 1 / 19 Basic idea Economic growth ! increased market size ! higher prots ! justies the xed costs of knowledge creation ! knowledge growth !

701 views • 19 slides
Endogenous labour supply, endogenous lifetime and economic growth: local and global indeterminacy

Endogenous labour supply, endogenous lifetime and economic growth: local and global indeterminacy

Endogenous labour supply, endogenous lifetime and economic growth: local and global indeterminacy Luca Gori 1 and Mauro Sodini 2 SIE October 23-25, 2014 *** 1. University of Genoa luca.gori@unige.it 2. University of Pisa

313 views • 30 slides
Neoclassical Models of Endogenous Growth October 2007 () Endogenous Growth October 2007 1 / 20

Neoclassical Models of Endogenous Growth October 2007 () Endogenous Growth October 2007 1 / 20

Neoclassical Models of Endogenous Growth October 2007 () Endogenous Growth October 2007 1 / 20 Motivation What are the determinants of long run growth? Growth in the "eectiveness of labour" should depend on economic incentives

360 views • 20 slides
3 New Indoor Positioning Solutions FOR AUTOMOTIVE TESTING 1. REFLECTIVE STRIP-AIDING

3 New Indoor Positioning Solutions FOR AUTOMOTIVE TESTING 1. REFLECTIVE STRIP-AIDING

3 New Indoor Positioning Solutions FOR AUTOMOTIVE TESTING 1. REFLECTIVE STRIP-AIDING Reflective strip-aiding offers a quick and cost-effective solution. How it works 1. Lay down reflective strips following a site survey. How it works

390 views • 11 slides
Topics and questions I should revise/answer: - Endogenous factor Factors affect the character of

Topics and questions I should revise/answer: - Endogenous factor Factors affect the character of

Key terms to revise : Topics and questions I should revise/answer: - Endogenous factor Factors affect the character of a place - Exogenous factor - Globalisation > Endogenous and endogenous factors > Factors that have affected

355 views • 16 slides
Catalytic Networks Mark Baumback Introduction Summary w Artificial Chemistry review w Self

Catalytic Networks Mark Baumback Introduction Summary w Artificial Chemistry review w Self

Catalytic Networks Mark Baumback Introduction Summary w Artificial Chemistry review w Self organization w Catalytic Networks n Autocatalytic Sets n Self Reproduction n Self Maintenance w Evolving autocatalytic sets (in a catalytic network) w

937 views • 54 slides
Reflective Parallel Programming Nicholas D. Matsakis, Thomas R. Gross ETH Zurich 1 Friday,

Reflective Parallel Programming Nicholas D. Matsakis, Thomas R. Gross ETH Zurich 1 Friday,

Reflective Parallel Programming Nicholas D. Matsakis, Thomas R. Gross ETH Zurich 1 Friday, June 18, 2010 Reflective Parallelism Reflection : Ability for a program to reason about its own structure Reflective Parallelism : Ability for

1.31k views • 118 slides
LN-13 From pin factory to endogenous growth. Looking backwards from Paul Romer to Adam Smith.

LN-13 From pin factory to endogenous growth. Looking backwards from Paul Romer to Adam Smith.

LN-13 From pin factory to endogenous growth. Looking backwards from Paul Romer to Adam Smith. Introduction One of the new breakthroughs in economics in recent decades has been endogenous growth theory . The out spring was Paul Romers article

286 views • 10 slides
Using CFD Modeling and Dosimetry as a Framework to Incorporate Endogenous Formation into a

Using CFD Modeling and Dosimetry as a Framework to Incorporate Endogenous Formation into a

Using CFD Modeling and Dosimetry as a Framework to Incorporate Endogenous Formation into a Chemical Assessment Jeff Schroeter Applied Research Associates Alliance for Risk Assessment Workshop May 28, 2013 Endogenous Chemical Risk Assessment:

377 views • 16 slides
Quality Ladders, Competition and Endogenous Growth Michele Boldrin and David K. Levine 1 The

Quality Ladders, Competition and Endogenous Growth Michele Boldrin and David K. Levine 1 The

Quality Ladders, Competition and Endogenous Growth Michele Boldrin and David K. Levine 1 The Standard Schumpeterian Competition Monopolistic Competition innovation modeled as endogenous rate of movement up a quality ladder

672 views • 38 slides
Developing teachers as creative, reflective professionals Paul Ellis Head of Teaching &

Developing teachers as creative, reflective professionals Paul Ellis Head of Teaching &

Workshop 2: Developing teachers as creative, reflective professionals Paul Ellis Head of Teaching & Learning Strategy Sri Lanka, December 2014 Being reflective To develop professionally, you must be able to reflect on your practice

382 views • 12 slides
Dummy Endogenous Variables in a Simultaneous Equation System Econometrica, Vol. 46, No. 4 (Jul.,

Dummy Endogenous Variables in a Simultaneous Equation System Econometrica, Vol. 46, No. 4 (Jul.,

Dummy Endogenous Variables in a Simultaneous Equation System Econometrica, Vol. 46, No. 4 (Jul., 1978), 931-959. James J. Heckman Econ 312, Spring 2019 Heckman 5/29/2019 1. A GENERAL MODEL FOR THE TWO EQUATION CASE Heckman Dummy Endogenous

764 views • 22 slides
Comparative statics Comparative statics is the study of how endogenous variables respond to

Comparative statics Comparative statics is the study of how endogenous variables respond to

Introduction The FOC approach Monotone comparative statics Producer applications Comparative statics Comparative statics is the study of how endogenous variables respond to changes in exogenous variables Endogenous variables are typically set

520 views • 13 slides
Potentialism about set theory ystein Linnebo University of Oslo SotFoM III, 2123 September

Potentialism about set theory ystein Linnebo University of Oslo SotFoM III, 2123 September

Potentialism about set theory ystein Linnebo University of Oslo SotFoM III, 2123 September 2015 ystein Linnebo (University of Oslo) Potentialism about set theory 2123 September 2015 1 / 23 Open-endedness in set theory But [the

895 views • 73 slides
Conjecturing over large corpora Thibault Gauthier Cezary Kaliszyk Josef Urban April 6, 2016 1

Conjecturing over large corpora Thibault Gauthier Cezary Kaliszyk Josef Urban April 6, 2016 1

Conjecturing over large corpora Thibault Gauthier Cezary Kaliszyk Josef Urban April 6, 2016 1 Goal Automatically discover conjectures in formalized libraries. Which formalized libraries ? theorems constants types theories Mizar 51086

587 views • 22 slides
FROM SURVIVING TO THRIVING AS AN ACCIDENTAL HOMESCHOOLER Melissa Gibson, PhD Marquette

FROM SURVIVING TO THRIVING AS AN ACCIDENTAL HOMESCHOOLER Melissa Gibson, PhD Marquette

FROM SURVIVING TO THRIVING AS AN ACCIDENTAL HOMESCHOOLER Melissa Gibson, PhD Marquette University College of Education WHATEVER YOU CHOOSE TO DO IS ENOUGH. WEBINAR OUTLINE WHATEVER YOU CHOOSE TO DO IS ENOUGH. [1] Our Context: COVID - 19

424 views • 27 slides
Intermetallic Clathrates A Challenge for Thermoelectrics Structure - Property Relations Peter

Intermetallic Clathrates A Challenge for Thermoelectrics Structure - Property Relations Peter

Intermetallic Clathrates A Challenge for Thermoelectrics Structure - Property Relations Peter Rogl 1 N. Melnychenko-Koblyuk 1 , A. Grytsiv 1 , E. Bauer 2 , H. Kaldarar 2 , H. Michor 2 F. Rhrbacher 2 , Royanian 1,2 , H. Schmidt 1 , G. Giester 3 1

1.31k views • 97 slides
Goals Understand the terms and ideas used in a modern, high-performance processor CS356 Unit

Goals Understand the terms and ideas used in a modern, high-performance processor CS356 Unit

12b.1 12b.2 Goals Understand the terms and ideas used in a modern, high-performance processor CS356 Unit 12b Various systems have different kinds of processors and you should understand the pros and cons of each kind of processor

588 views • 16 slides
Housing Task Force Report Presentation to Metro Cities Housing and Economic Development

Housing Task Force Report Presentation to Metro Cities Housing and Economic Development

Housing Task Force Report Presentation to Metro Cities Housing and Economic Development Committee 8/22/18 1 Our Vision Every Minnesotan has a place to live in a thriving community and livability remains a hallmark and competitive

402 views • 16 slides
Color Centers as Direct DM Detectors Ranny Budnik Weizmann Institute of Science Collaborators:

Color Centers as Direct DM Detectors Ranny Budnik Weizmann Institute of Science Collaborators:

Color Centers as Direct DM Detectors Ranny Budnik Weizmann Institute of Science Collaborators: T. Volansky, O. Cheshnovsky, O. Slone, A. Kreisel, A. Soffer H. Landsman, N. Priel, Y. Mosbacher, M. Weiss R. Budnik, DoE 3/2017 The goal: Open a

571 views • 24 slides
Intro to Image Based Rendering Intro to Image Based Rendering Working with images Working with

Intro to Image Based Rendering Intro to Image Based Rendering Working with images Working with

Intro to Image Based Rendering Intro to Image Based Rendering Working with images Working with images realistic appearance textures inflexible? 1 References References Two classic papers (available through the ACM web site:

398 views • 18 slides

More recommend