Center for Analysis and Design of Intelligent Agents

Note: PAGE UNDER CONSTRUCTION
Note: DO NOT SKIP READING THE BELOW TEXT

This material is generally ordered by specificity (both within and between headings), starting with the general topic of what intelligence is, progressing towards good old-fashioned AI (aka constructionist AI or GOFAI) and then onward towards artificial general intelligence (AGI). Within each topic the papers are ordered by importance, the most important first.

The recommended minimum number of papers to be read in each category is listed in brackets [ a,b ] after the title, where a refers to the necessary mandatory number of papers to be read, and b refers to the recommended absolute minimum number (papers are ordered from most to least important, so start counting from the top). If no number is given you should read all the papers listed. The section marked “Prerequisites” are readings on the basics: Things you should already know. If you even have the slightest reason to think that some content in these is not already under your belt (e.g. you have neither recently taken an introductory course on AI nor a single psychology or philosophy course on intelligence) you really should read them (they are a quick read, for the most part).

This means you are expected to read well over 50 papers in this course, so that comes out to at least 3-4 papers per week (5 recommended). Keep at it and you'll be fine!

Note: Assigned readings should be read before class. There is a simple reason for that: You will have some familiarity with the subject matter which not only means you will remember it better but also that you can ask questions for clarification during the lecture and partially steer its direction. Reading the papers after class is less effective. Warning: Do not attempt to read them during class - this is absolutely the worst way to cover this material (but of course you may have it open for reference). Reading the assigned readings not at all should generally be avoided.

As you read papers from each of the following categories I want you ask yourself a few questions:

• 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 (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.

• The g factor on Wikipedia.
• Multiple theory of intelligence on Wikipedia.

• A Collection of Definitions of Intelligence by Legg & Hutter.
• Evolution, Learning & Culture: Computational Metaphors for Adaptive Algorithms by R. K. Belew
• A Computational Foundation for the Study of Cognition by D. Chalmers
• Architectural Requirements for Human-like Agents Both Natural and Artificial by Sloman, A.
• 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).
  • Alex the Parrot on YouTube (video repeats halfway). Alex on Wikipedia
  • Koko the Gorilla on YouTube. Koko on Wikipedia
  • Bumblebees learn by observation on YouTube. Paper on Bumblebees learning by observation by Loukola et al.
  • Why Aren't Elephants Smarter Than Humans Since Their Brains Are Bigger? by Fabian van den Berg
  • Parrots vs. Children BBC Earth on YouTube
  • Crow solving an 8-step puzzle on YouTube
  • Crow demonstrates causal understanding on YouTube
  • TED talk on crow intelligence by John Marzluff

• Artificial General Intelligence on Wikipedia.
• Four Basic Questions about Artificial Intelligence by P. Wang.
• What Is AI? by J. McCarthy.

• On Defining Artificial Intelligence, Journal of Artificial General Intelligence 10(2):1-37 by Pei Wang.
• Essentials of General Intelligence: The Path Towards AGI by P. Voss.
• Requirements for deliberative systems by A. Sloman – key sections: from 8 onwards.
• Computing Machinery and Intelligence by A. Turing.
• Three Fundamental Misconceptions of Artificial Intelligence by Pei Wang.
• An integrated theory of mind by Anderson et al.
• Universal Intelligence: A Definition of Machine Intelligence by Shane Legg and Marcus Hutter.

• Reinforcement Learning in the Encyclopedia of Cognitive Science by Peter Dayan and Christopher Watkins.
• 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: Rich Sutton's FAQ.
• Deep learning on Wikipedia (Sections: Intro, Overview, and Neural Networks).
• Introduction to RL video by D. Silvers.
• Control systems: 'Type' and 'order' on Wikibooks

• Introduction to Software Architecture by Garlan & Shaw.
• Constructionist Design Methdology paper by K.R. Thórisson.
• Subsumption Architecture on Wikipedia.
• A Robust Layered Control System for a Mobile Robot by R. Brooks.
• BDI Architecture on Wikipedia.
• BDI Agents: From Theory to Practice by A.S. Rao & M.P. Georgeff.
• How to Build Complete Creatures Rather than Isolated Cognitive Simulators by Rodney Brooks
• A Mind Model for Multimodal Communicative Creatures and Humanoids by Thórisson, K. R.
• Whatever happened to the subsumption architecture? by Simon Birrell

• Architectural Mismatch or Why it’s hard to build systems out of existing parts by Garlan, D., R. Allen and J. Ockerbloom. Also available here.
• Reductio ad Absurdum: On Oversimplification in Computer Science & its Pernicious Effect on Artificial Intelligence Research by K. R. Thórisson.
• ROBERT ROSEN’S ANTICIPATORY SYSTEMS THEORY: THE ART AND SCIENCE OF THINKING AHEAD by J. Rosen.
• The very laws of physics imply that artificial intelligence must be possible. What's holding us up? by D. Deutch.

• What is AGI? by K. R. Thórisson.
• Introduction: Aspects of Artificial General Intelligence by P. Wang & B. Goerzel (first 3 sections)
• Cognitive architectures: Research issues and challenges by Langley, P., Laird, J.E., Rogers, S.
• Mapping the Landscape of Human-Level Artificial General Intelligence by Adams et al.
• What Must a World Be Like That a Human-Like Intelligence May Develop In It? by B. Goertzel.
• (ACT-R) An Integrated Theory of the Mind by Anderson, J. R.; Bothell, D.; Byrne, M.D.; Douglass, S.; Lebiere, C. & Qin, Y.

Related to: Methodology, Cognitive Architectures

• Cognitive Architecture Requirements for Achieving AGI by J.E. Laird et al.
• Architectural Requirements for Human-like Agents Both Natural and Artificial by A. Sloman
• Cognitive architectures: Research issues and challenges. by Langley, P., Laird, J.E., Rogers, S. (2009). Cognitive Systems Research Vol 10(2), pp. 141-160.
• Holistic Intelligence: Transversal Skills & Current Methodologies by K.R. Thórisson & E. Nivel.
• Towards a Complete, Multi-level Cognitive Architecture by R. Wray et al.

Related to: Cognitive Architecture, Intelligence, Understanding, AI

• What is Thought? by Ezequiel Morsella
• Thought on Wikipedia.
• Animal Cognition on Wikipedia.
• Podcast interview with Jeff Hawkins by L. Friedman
• Predictive Heuristics for Decision-Making in Real-World Environments by H. Helgason et al.

Related to: Thought, Reasoning

• About Understanding by K. R. Thorisson et al.
• Evaluating Understanding by K.R. Thórisson & J. Bieger
• Understanding & Common Sense by K. R. Thórisson & D. Kremelberg
• Do Machines Understand? A Short Review of Understanding & Common Sense in Artificial Intelligence by K.R. Thórisson & D. Kremelberg

Related to: Symbols, Meaning, Autonomy, Bootstrapping

• When is a cognitive system embodied? by Riegler
• Does a Laptop Have a Body? by P. Wang.
• Social situatedness by Lindblom & Ziemke

Related to: Bootstrapping / Self-Programming

• Fridges, Elephants, and the Meaning of Autonomy and Intelligence by R. Sanz et al.
• Cognitive Architectures & Autonomy: A Comparative Review by K.R. Thórisson & H.P. Helgason
• Towards a Programming Paradigm for Control Systems With High Levels of Existential Autonomy by E. Nivel & K. R. Thórisson.
• A Framework for Autonomy Levels for Unmanned Systems (ALFUS) by Huang et al.
• The Emergence of Artificial Intelligence: Learning to Learn by P. Bock.

Related to: Cognitive Architecture, Learning

• Principles of Integrated Cognitive Control by R. Sanz et al.
• On Attention Mechanisms for AGI Architectures: A Design Proposal by Helgason et al.; accompanying video can be found here.
• Self-awareness in Real-time Cognitive Control Architectures by Sanz, R., López, I. & Hernández, C.
• A model of attention that takes global scene factors into account by Torralba.
• Towards a Programming Paradigm for Control Systems with High Levels of Existential Autonomy by E. Nivel et al.
• Predictive Heuristics for Decision-Making in Real-World Environments by H. Helgason et al.
• Towards a General Attention Mechanism for Embedded Intelligent Systems by H. P. Helgason et al.
• A three-layer model of selective attention by Mancas et al.
• Attention Capabilities for AI Systems by H. P. Helgason & K. R. Thórisson.

Related to: Reasoning, Learning, Bootstrapping

• Self-Programming: Operationalizing Autonomy by Nivel, E. & K. R. Thórisson.
• Von Neumann Universal Constructor on Wikipedia.
• Towards a Programming Paradigm for Control Systems With High Levels of Existential Autonomy by E. Nivel & K. R. Thórisson.
• Behavioral Self-Programming by Reasoning by Wang, P.

Related to: Thought, Cognitive Architecture, Intelligence

• Return to Term Logic by Pei Wang.
• Abduction in Non-Axiomatic Logic by Pei Wang.
• A New Approach for Induction: From a Non-Axiomatic Logical Point of View by Pei Wang
• Critical Reasoning by Marianne Talbot
• Wason's Cards: What is Wrong? by P. Wang.
• Abduction & Deduction With Causal-Relational Models by K.R. Thórisson et al.

Related to: Cognitive Architecture, Intelligence

• Bounded Seed-AGI by E. Nivel et al.
• From Seed AI to Technological Singularity via Recursively Self-Improving Software by R. V. Yampolskiy.
• Creating a Child Machine: Reflections on Turing’s Proposal by Raj Reddy
• Nursing Turing’s Child Machine: Towards Communication-Based Artificial Intelligence by Maco Baroni et al.

Related to: Resource control, Attention, Reasoning

• Growing Recursive Self-Improvers by B. Steunebrink et al.
• Cumulative Learning by K.R. Thórisson et al.
• The Logic of Learning by P. Wang.
• The Emergence of Artificial Intelligence: Learning to Learn by P. Bock.
• Cumulative Learning With Causal-Relational Models by K.R.Thórisson et al.

Related to: Learning, Bootstrapping

• The Pedagogical Pentagon by Jordi Bieger et al.
• Raising AI: Tutoring Matters by Jordi Bieger, Kristinn R. Thórisson and Deon Garrett
• Matching Learning Style to Instructional Method: Effects on Comprehension by Rogowsky et al.
• Machine teaching: An inverse problem to machine learning and an approach toward optimal education by Xiaojin Zhu
• Models of cooperative teaching and learning by Sarah Zilles, Steffen Lange, Robert Holte and Martin Zinkevich
• Bringing up Turing's 'Child-Machine' by S. G. Sterrett
• Teaching on a Budget: Agents Advising Agents in Reinforcement Learning by Lisa Torrey and Matthew E. Taylor
• Curriculum learning by Yoshua Bengio, Jérôme Louradour, Ronan Collobert and Jason Weston

Related to: Cognitive Architecture, Implemented AGI Systems

• Constructivist AI (CAIM)
• A New Constructivist AI: From Manual Construction to Self-Constructive Systems by K.R. Thórisson
• Can there be a science of complex systems? by H. A. Simon
• Every Good Regulator of a System Must be a Model of that System by Conant & Ashby.
• A Primer For Conant & Ashby's “Good-Regulator Theorem” by Daniel L. Scholten
• Approaches & Assumptions of Self-Programming in Achieving Artificial General Intelligence by Thórisson et al.
• Cybernetics and Second-Order Cybernetics by Heylighen, F. & C. Joslyn
• Does the Future of AGI Lie in Cognitive Synergy? by B. Goertzel

• From NARS to a thinking machine by P. Wang
• What is NARS by K. R. Thórisson
• Introduction to NARS by P. Wang
• NARS intro paper by P. Wang
• NARS demos by P. Wang

• Achieving Artificial General Intelligence Through Peewee Granularity by Thórisson, K. R. & Nivel, E.
• Bounded Seed-AGI by E. Nivel et al.
• Autonomous Acquisition of Natural Communication by K. R. Thórisson et al.
• Anytime Bounded Rationality by E. Nivel et al.
• Bounded Recursive Self-Improvement by E. Nivel et al.
• Self-Programming: Operationalizing Autonomy by Nivel, E. & K. R. Thórisson.

• The Sigma Cognitive Architecture and System by P. S. Rosenbloom.

• OPENCOG PRIME: A COGNITIVE SYNERGY BASED ARCHITECTURE FOR ARTIFICIAL GENERAL INTELLIGENCE by Ben Goerzel.
• Getting Started with Open Cog by Ben Goerzel.

• 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. PDF
• Anderson, J.R. & Schunn, C.D. (2000). Implications of the ACT-R learning theory: No magic bullets. Advances in instructional psychology. 5:1-34. Lawrence Erlbaum | PDF
• Laird, J.E.; Newell, A. & Rosenbloom, P.S. (1987). SOAR: An architecture for general intelligence. Artificial Intelligence, Volume 33, Issue 1, Pages 1-64 PDF
• Snaider, J; McCall, R. & Franklin, S. (2011). The LIDA framework as a general tool for AGI. Artificial General Intelligence, Lecture Notes in Computer Science. 2011. Volume 6830/2011. pp. 133-142 PDF
• J. Schmidhuber (2016). Learning how to Learn Learning Algorithms: Recursive Self-Improvement. - slides

• Evaluation of General-Purpose Artificial Intelligence: Why, What & How by J. Bieger et al.
• Towards Flexible Task-Environments For Comprehensive Evaluation of Artificial Intelligent Systems & Automatic Leaners by K. R. Thórisson et al.
• Why Artificial Intelligence Needs a Task Theory — And What It Might Look Like by K. R. Thórisson et al.
• BAYESIANISM AND CAUSALITY, OR, WHY I AM ONLY A HALF-BAYESIAN by J. Pearl
• A New AI Evaluation Cosmos: Ready to Play the Game? by J. Hernandez-Orallo et al.
• Hybrid systems on Wikipedia.
• The Toy Box Problem by Johnston
• Loebner Prize article by Charlie Moloney.
• FraMoTEC: Modular Task-Environment Construction Framework for Evaluating Adaptive Control Systems by Thorarensen et al.
• The Lovelace Test by M. Reidl.
• Psychometric Artificial General Intelligence: The Piaget-MacGuyver Room by Bringsjord, S. & Licato, J. In Theoretical Foundations of Artificial General Intelligence, edited by P. Wang and B. Goertzel (Atlantis Press).
• Time, Clocks, and the Ordering of Events in a Distributed System by L. Lamport.
• Hybrid Dynamical Systems by R. Goebel et al.
• AGI Preschool: A Framework for Evaluating Early-Stage Human-like AGIs by Goertzel, B. & Bugaj, S. V. Proceedings of the Second Conference on Artificial General Intelligence, Atlantis Press.
• Theory of Hybrid Automata by T. A. Henzinger.
• HYBRID SYSTEMS: GENERALIZED SOLUTIONS AND ROBUST STABILITY by R. Goebel et al.

• Searle's Chinese Room Argument on the Internet Encyclopedia of Philosophy
• The Chinese Room on Wikipedia

• The Physical Symbol System Hypothesis: Status & Prospects by N. J. Nilsson.
• Minds, Brains & Programs by John Searle
• Subsymbolic Computation and the Chinese Room by D. Chalmers
• Syntactic Autonomy - Or Why There is no Autonomy Without Symbols and how Self-Organizing Systems Might Evolve Them by L. M. Rocha
• The Physics of Symbols: Bridging the Epistemic Cut by H. H. Pattee
• The 'Cybernetic Cut': Progressing from Description to Prescription in Systems Theory by D. L. Abel

• Selected Self-Organization and the Semiotics of Evolutionary Systems by L. M. Rocha
• Weak Emergence by M. A. Bedau

• What's it Like to be a Bat? by T. Nagel
• Consciousness and its Place in Nature by D. J. Chalmers
• The Future of Consciousness - TEDx lecture by R. Hameroff
• Consciousness is a Mathematical Pattern - TEDx lecture by M. Tegmark
• Consciousness and the Brain - TEDx lecture by J. Searle

• Leave no dark corner by Matthew Carney.
• THE FUTURE OF EMPLOYMENT: HOW SUSCEPTIBLE ARE JOBS TO COMPUTERISATION? by Frey and Osborne

• Reinforcement Learning: An Introduction by Rich Sutton and Andrew Barto (1998) is the introductory text on RL.
• Machine Super Intelligence is Shane Legg's 2008 PhD thesis. While it is not on reinforcement learning, it does connect the concepts of RL to AI, what he calls “universal AI”.
• Reinforcement Learning is a full Udacity course on RL from Georgia Tech.
• A Short Course on Reinforcement Learning by Satinder Singh at MLSS'11 introduces RL and discusses some important shortcomings and proposed first steps to solving them.
• 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.
• 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.
• Resource-Bounded Machines are Motivated to be Effective, Efficient & Curious by B. Steunebrink

• A gentle introduction to neural networks - gives a good overview of the different approaches

• Kognit: Intelligent Cognitive Enhancement Technology by Cognitive Models and Mixed Reality for Dementia Patients by D. Sonntag and accompanying video
• Comparison table of cognitive architectures, courtesy of BICA Society / Alexei Samsonovich
• Why are so many smart people such idiots about philosophy? by O. Goldhill
• Cognitive Map Architecture: Facilitation of Human-Robot Interaction in Humanoid Robots by V. Ng-Thow-Hing et al. (2009).
• Toward a unified artificial intelligence by Wang, P.
• Judea Pearl lecture on Causation on YouTube
• Creativity in a Nutshell by M. Boden.
• Militello, L.G., Dominguez, C.O., Lintern, G. & Klein, G. (2010). The Role of Cognitive Systems Engineering in the Systems Engineering Design Process. In Systems Engineering, Vol 13(3), pp. 261-273. PDF
• Pan, S. J. & Yang, Q. (2011). A survey on transfer learning. IEEE Transactions on Knoweledge and Data Engineering, 22(10), pp. 1345–1359. PDF
• Sanz, R., Hernandez, C., Gomez, J., Bermejo-Alonso, J., Rodriguez, M., Hernando, A. & Sanchez, G. (2009). Systems, models and self-awareness: Towards architectural models of consciousness. International Journal Of Machine Consciousness, 1(2), pp.255–279. PDF
• Silver, D.L. & Poirier, R. (2007). Requirements for Machine Lifelong Learning. IWINAC, LNCS (4527), pp.313-319. PDF
• PHYSICALISM, EMERGENCE AND DOWNWARD CAUSATION by Campbell and Bickhard
• Man as Machine - Joscha Bach's AGI intro lecture at AGI Summer School 2009
• Mastering the game of Go with deep neural networks and tree search by Silver, Huang et al. (DeepMind)
• Why Philosophers Should Care About Computational Complexity by S. Aaronsson
• A Vision for Computer Science - the System Perspective by J. Sifakis

• Journal of Artificial General Intelligence
• Introduction to Artificial Intelligence - A Modern Approach by S. Russell & P. Norvig
• Chapter 1: An Introduction to Philosophy of Science by Malcolm Forster

EOF