Differences

This shows you the differences between two versions of the page.

--- public:t-720-atai:atai-19:readings [2019/09/02 09:11] – [The Holy Grail of AI: Generality] thorisson
+++ public:t-720-atai:atai-19:readings [2024/04/29 13:33] (current) – external edit 127.0.0.1
@@ Line 19: / Line 19: @@
 **As you read papers from each of the following categories I want you ask yourself a few questions:**
-  * For each category X, ask:
+  * For each paper in each category X, ask yourself:
     * What is X?
     * How does the human mind do X?
     * Do current computers do X?
     * ...and ...
-    * Do we need X to create a machine that rivals the ability of humans to do X?
+    * Do we need (to replicate or capture) what the human mind does to achieve X to create a machine that rivals the ability of humans to do X?
 If you can answer them satisfactorily when you're done reading you're good! Even if you can't you'll be fine if you: Write down the discrepacies and //bring them to class in the form of questions//. There is no such thing as a 'stupid question' when you're learning something new.
 \\
 \\
 \\
+===== Intelligence =====
-==== Intelligence ====
+====Prerequisites====
-===Prerequisites===
   * [[http://en.wikipedia.org/wiki/General_intelligence_factor| The g factor]] on Wikipedia.
   * [[http://en.wikipedia.org/wiki/Theory_of_multiple_intelligences| Multiple theory of intelligence]] on Wikipedia.
-===Key Papers===
+====Key Papers====
   * [[http://www.vetta.org/documents/A-Collection-of-Definitions-of-Intelligence.pdf|A Collection of Definitions of Intelligence]] by Legg & Hutter.
@@ Line 46: / Line 47: @@
   * [[http://consc.net/papers/emergence.pdf|Strong and Weak Emergence]] by D. Chalmers
   * Animals //(you are encouraged to find other material on these topics - please let instructor know if you find some good stuff)//.
-    * [[https://www.youtube.com/watch?v=dKvVaRlz0Y4|Alex the Parrot]] on YouTube (video repeats halfway).  [[https://en.wikipedia.org/wiki/Alex_(parrot)|Alex on Wikipedia]] |
+    * [[https://www.youtube.com/watch?v=dKvVaRlz0Y4|Alex the Parrot]] on YouTube (video repeats halfway).  [[https://en.wikipedia.org/wiki/Alex_(parrot)|Alex on Wikipedia]]
-    * [[https://www.youtube.com/watch?v=SNuZ4OE6vCk|Koko the Gorilla]] on YouTube.  [[https://en.wikipedia.org/wiki/Koko_(gorilla)|Koko on Wikipedia]] |
+    * [[https://www.youtube.com/watch?v=SNuZ4OE6vCk|Koko the Gorilla]] on YouTube.  [[https://en.wikipedia.org/wiki/Koko_(gorilla)|Koko on Wikipedia]]
+    * [[https://www.youtube.com/watch?v=exsrX6qsKkA|Bumblebees learn by observation]] on YouTube. [[https://www.researchgate.net/publication/272748457_Information_transfer_beyond_the_waggle_dance_Observational_learning_in_bees_and_flies|Paper on Bumblebees learning by observation]] by Loukola et al.
     * [[https://apple.news/AQEvvY_wbRdqE1J-3MU_6WQ|Why Aren't Elephants Smarter Than Humans Since Their Brains Are Bigger?]] by Fabian van den Berg
     * [[https://www.youtube.com/watch?v=BG-0Bpe0J34|Parrots vs. Children]] BBC Earth on YouTube
@@ Line 55: / Line 57: @@
 \\
 \\
-==== Deifinitions of Artificial Intelligence ====
+==== Definitions of Artificial Intelligence ====
 ===Prerequisites===
@@ Line 74: / Line 76: @@
 \\
-==== Constructionist Systems & Methodologies ====
+===== Constructionist Systems & Methodologies =====
-===Prerequisites===
+====Prerequisites====
   * [[http://www.gatsby.ucl.ac.uk/~dayan/papers/dw01.pdf|Reinforcement Learning in the Encyclopedia of Cognitive Science]] by Peter Dayan and Christopher Watkins.
   * [[http://www.ualberta.ca/~szepesva/RLBook.html|Algorithms for Reinforcement Learning]] by Csaba Szepesvári (2010) is a much more recent, shorter book that discusses the strengths and weaknesses of various RL algorithms. See also: [[http://incompleteideas.net/sutton/RL-FAQ.html|Rich Sutton's FAQ]].
-  * [[https://en.wikipedia.org/wiki/Deep_learning|Deep learning on Wikipedia]] (Chapters: Intro, Overview, and Neural Networks).
+  * [[https://en.wikipedia.org/wiki/Deep_learning|Deep learning on Wikipedia]] (Sections: Intro, Overview, and Neural Networks).
   * [[https://www.youtube.com/watch?v=2pWv7GOvuf0|Introduction to RL]] video by D. Silvers.
+  * [[https://en.wikibooks.org/wiki/Control_Systems/System_Metrics|Control systems: 'Type' and 'order']] on Wikibooks
-=== Introductory Material - Constructionist AI [ 2,3 ] ===
+==== Introductory Material - Constructionist AI [ 2,3 ] ====
   * {{:public:intro_to_software_arch.pdf| Introduction to Software Architecture}} by Garlan & Shaw.
@@ Line 92: / Line 95: @@
   * [[http://people.csail.mit.edu/brooks/papers/how-to-build.pdf|How to Build Complete Creatures Rather than Isolated Cognitive Simulators]] by Rodney Brooks
   * [[http://alumni.media.mit.edu/%7Ekris/ftp/IJAAI.pdf|A Mind Model for Multimodal Communicative Creatures and Humanoids]] by Thórisson, K. R.
+  * [[http://www.artificialhumancompanions.com/robot-mind-robot-body-whatever-happened-subsumption-architecture/|Whatever happened to the subsumption architecture?]] by Simon Birrell
+==== Limitations of Constructionist AI [ 2,4 ] ====
-=== Limitations of Constructionist AI [ 2,4 ] ===
   * {{:public:archmismatch-icse17.pdf| Architectural Mismatch or Why it’s hard to build systems out of existing parts}} by Garlan, D., R. Allen and J. Ockerbloom. Also available [[http://www.cs.cmu.edu/afs/cs/project/able/ftp/archmismatch-icse17/archmismatch-icse17.pdf|here]].
@@ Line 104: / Line 108: @@
 \\
 \\
-==== The Holy Grail of AI: Generality ====
+===== The Holy Grail of AI: Generality =====
-=== Overview of Artificial General Intelligence [ 4,5 ] ===
+==== Overview of Artificial General Intelligence [ 4,5 ] ====
   * [[http://cadia.ru.is/wiki/public:t720-atai-2012:what_is_agi|What is AGI?]] by K. R. Thórisson.
@@ Line 115: / Line 119: @@
   * [[http://act-r.psy.cmu.edu/wordpress/wp-content/uploads/2012/12/526FSQUERY.pdf|(ACT-R) An Integrated Theory of the Mind]] by Anderson, J. R.; Bothell, D.; Byrne, M.D.; Douglass, S.; Lebiere, C. & Qin, Y.
-=== Requirements for AGI [ 3,5 ] ===
+==== Requirements for AGI [ 3,5 ] ====
 Related to: //Methodology, Cognitive Architectures//
@@ Line 124: / Line 128: @@
   * [[https://iccm-conference.neocities.org/2007/files/wray__lebiere__weinstein__jha__springer__belding__best____van_parunak.pdf| Towards a Complete, Multi-level Cognitive Architecture]] by R. Wray et al.
-=== Thought, Cognition, Cognitive Process/es ===
+==== Thought, Cognition, Cognitive Process/es ====
 Related to: //Cognitive Architecture, Intelligence, Understanding, AI //
   * [[https://www.psychologytoday.com/intl/blog/consciousness-and-the-brain/201202/what-is-thought|What is Thought?]] by Ezequiel Morsella
   * [[https://en.wikipedia.org/wiki/Thought|Thought]] on Wikipedia.
   * [[https://en.wikipedia.org/wiki/Animal_cognition|Animal Cognition]] on Wikipedia.
-  * [[http://alumni.media.mit.edu/~kris/ftp/Helgason%20et%20al-AGI2013.pdf|Predictive Heuristics for Decision-Making in Real-World Environments]] by H. Helgason et al.
+  * [[https://lexfridman.com/?powerpress_pinw=3920-podcast|Podcast interview with Jeff Hawkins]] by L. Friedman
+  * [[http://alumni.media.mit.edu/~kris/ftp/Helgason%20et%20al-AGI2013.pdf|Predictive Heuristics for Decision-Making in Real-World Environments]] by H. Helgason et al.
-=== Understanding [ 3,4 ]===
+==== Understanding [ 3,4 ]====
 Related to: //Thought, Reasoning//
   * [[http://alumni.media.mit.edu/~kris/ftp/AGI16_understanding.pdf|About Understanding]] by K. R. Thorisson et al.
   * [[http://alumni.media.mit.edu/~kris/ftp/IJCAI17-EGPAI-EvaluatingUnderstanding.pdf|Evaluating Understanding]] by K.R. Thórisson & J. Bieger
-  * [[http://alumni.media.mit.edu/~kris/ftp/AGI17_Understanding&CommonSense.pdf|Understanding & Common Sense]] by K. R. Thórisson & J. Bieger
+  * [[http://alumni.media.mit.edu/~kris/ftp/AGI17_Understanding&CommonSense.pdf|Understanding & Common Sense]] by K. R. Thórisson & D. Kremelberg
   * [[http://alumni.media.mit.edu/~kris/ftp/AGI17-UUW-DoMachinesUnderstand.pdf|Do Machines Understand? A Short Review of Understanding & Common Sense in Artificial Intelligence]]  by K.R. Thórisson & D. Kremelberg
-=== Situatedness, Embodiment [ 1,2 ] ===
+==== Situatedness, Embodiment [ 1,2 ] ====
 Related to: //Symbols, Meaning, Autonomy, Bootstrapping //
@@ Line 150: / Line 155: @@
-=== Autonomy [ 3,4 ]===
+==== Autonomy [ 3,4 ]====
 Related to: //Bootstrapping / Self-Programming//
@@ Line 160: / Line 165: @@
-=== Resource Control: Attention / Self-Control / Integrated Cognitive Control [ 4,5 ] ===
+==== Resource Control: Attention / Self-Control / Integrated Cognitive Control [ 4,6 ] ====
 Related to: //Cognitive Architecture, Learning//
@@ Line 168: / Line 173: @@
   * [[http://web.mit.edu/torralba/www/josa.pdf| A model of attention that takes global scene factors into account]] by Torralba.
   * [[http://alumni.media.mit.edu/~kris/ftp/nivel_thorisson_replicode_AGI13.pdf| Towards a Programming Paradigm for Control Systems with High Levels of Existential Autonomy]] by E. Nivel et al.
+  * [[http://alumni.media.mit.edu/~kris/ftp/Helgason%20et%20al-AGI2013.pdf|Predictive Heuristics for Decision-Making in Real-World Environments]] by H. Helgason et al.
   * [[http://alumni.media.mit.edu/~kris/ftp/HelgasonEtAl-2014-Attention-IJCSAI10339-20140314-163624-3675-40677.pdf|Towards a General Attention Mechanism for
 Embedded Intelligent Systems]] by H. P. Helgason et al.
@@ Line 174: / Line 180: @@
-=== Self-Programming [ 4,6 ] ===
+==== Self-Programming [ 4,5 ] ====
 Related to: //Reasoning, Learning, Bootstrapping//
@@ Line 183: / Line 189: @@
-=== Reasoning  [ 4,6 ]===
+==== Reasoning  [ 4,6 ]====
 Related to: //Thought, Cognitive Architecture, Intelligence//
@@ Line 194: / Line 200: @@
-=== (AGI) Bootstrapping / Seed A(G)I / Seed Programming [ 2,4 ] ===
+==== (AGI) Bootstrapping / Seed A(G)I / Seed Programming [ 2,4 ] ====
 Related to: //Cognitive Architecture, Intelligence//
@@ Line 200: / Line 206: @@
   * [[http://arxiv.org/pdf/1502.06512.pdf|From Seed AI to Technological Singularity via Recursively Self-Improving Software]] by R. V. Yampolskiy.
   * [[https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=47&cad=rja&uact=8&ved=2ahUKEwihyfrQ96PdAhXsLsAKHbNRDh4QFjAuegQISxAC&url=http%3A%2F%2Fwww.rr.cs.cmu.edu%2FCreating%2520a%2520Child%2520Machine.docx&usg=AOvVaw3ZIHWfvIoKnZF1fNf7A_EI|Creating a Child Machine: Reflections on Turing’s Proposal]] by Raj Reddy
-  * [[https://mainatnips.github.io/mainatnips.github.io/slides/baroni-nursing-turing.pdf|Nursing Turing’s Child Machine: Towards Communication-based Artificial Intelligence]] by Maco Baroni et al.
+  * [[https://mainatnips.github.io/mainatnips.github.io/slides/baroni-nursing-turing.pdf|Nursing Turing’s Child Machine: Towards Communication-Based Artificial Intelligence]] by Maco Baroni et al.
-=== Learning ===
+==== Learning ====
 Related to: //Resource control, Attention, Reasoning//
   * [[http://alumni.media.mit.edu/~kris/ftp/AGI16_growing_recursive_self-improvers.pdf|Growing Recursive Self-Improvers]] by B. Steunebrink et al.
@@ Line 212: / Line 218: @@
-=== Artificial Pedagogy [ 2,4 ] ===
+==== Artificial Pedagogy [ 2,4 ] ====
 Related to: //Learning, Bootstrapping//
@@ Line 225: / Line 231: @@
-=== AGI Methodology [ 5,6 ] ===
+==== AGI Methodology [ 5,6 ] ====
 Related to: //Cognitive Architecture, Implemented AGI Systems //
@@ Line 239: / Line 245: @@
 \\
 \\
-====Implemented AGI-Aspiring Systems====
+=====Implemented AGI-Aspiring Systems=====
-=== NARS [ 4,5 ] ===
+==== NARS [ 4,5 ] ====
   * [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.134.4298&rep=rep1&type=pdf|From NARS to a thinking machine]] by P. Wang
@@ Line 250: / Line 256: @@
-=== AERA [ 5,5 ]===
+==== AERA [ 5,5 ]====
   * [[http://alumni.media.mit.edu/~kris/ftp/PeeweeGranularity-Thorisson-Nivel-09.pdf|Achieving Artificial General Intelligence Through Peewee Granularity]] by Thórisson, K. R. & Nivel, E.
@@ Line 260: / Line 266: @@
-=== Sigma [ 0,1 ] ===
+==== Sigma [ 0,1 ] ====
   * [[http://cs.usc.edu/~rosenblo/Pubs/Sigma%20AISBQ%20D.pdf|The Sigma Cognitive Architecture and System]] by P. S. Rosenbloom.
-=== Open Cog [ 0,2 ] ===
+==== Open Cog [ 0,2 ] ====
   * [[http://goertzel.org/dynapsyc/2009/OpenCogPrime.pdf|OPENCOG PRIME: A COGNITIVE SYNERGY BASED ARCHITECTURE FOR ARTIFICIAL GENERAL INTELLIGENCE]] by Ben Goerzel.
   * [[http://wiki.opencog.org/w/Getting_Started|Getting Started with Open Cog]] by Ben Goerzel.
-=== Other Such Systems [ 0,3 ] ===
+==== Other Such Systems [ 0,3 ] ====
   * Franklin, S. (2007). **(LIDA) A Foundational Architecture for Artificial General Intelligence**. Advances in Artificial General Intelligence: Concepts, Architectures and Algorithms. IOS Press, Amsterdam, The Netherlands, The Netherlands, pp. 36-54. [[http://goertzel.org/agiri06/%5B4%5D%20StanFranklin.pdf | PDF]]
@@ Line 280: / Line 286: @@
 \\
-==== Evaluation: Worlds, Tasks, Environments [ 3,6 ] ====
+===== Evaluation: Worlds, Tasks, Environments [ 3,6 ] =====
   * [[http://alumni.media.mit.edu/~kris/ftp/EGPAI_2016_paper_9.pdf|Evaluation of General-Purpose Artificial Intelligence: Why, What & How]] by J. Bieger et al.
@@ Line 353: / Line 359: @@
   * [[http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html|Advanced Topics: RL]] by David Silver is a more in-depth, modern RL course from one of the people who worked on Google DeepMind's Atari playing system that received a lot of (media) attention.
   * [[http://videolectures.net/nips09_littman_mbrl/|Model-Based Reinforcement Learning]] is a tutorial given by Michael Littman at NIPS'09 about model-based RL, which is a lot less common than model-free RL, but not less interesting.
+  * [[http://link.springer.com/chapter/10.1007/978-3-642-39521-5_13#page-1|Resource-Bounded Machines are Motivated to be Effective, Efficient & Curious]] by B. Steunebrink
 === Deep Learning [ 0,1 ]===