Bibliography

This bibliography lists more than 250 books, papers, and book chapters relevant to intelligence explosion. Most entries are available online; links are provided.

Core Readings and works that discuss multiple topics are listed multiple times (under different headings). Core Readings are listed alphabetically. All Readings are listed chronologically, for easy location of older and newer works. (Because this is a web document, a visitor may use the 'Find' function to quickly locate all documents by a particular author.)

Contents:

• Core Readings
• All Readings
  • Intelligence Explosion
  • Technological Forecasting
  • Risks of Intelligence Explosion
  • Artificial General Intelligence Programming
  • Whole Brain Emulation

Core Readings

Chalmers (2010). The Singularity: A Philosophical Analysis. Journal of Consciousness Studies, 17: 7-65.

Chalmers formalizes I.J. Good's argument for the intelligence explosion and examines each premise in turn. He discusses possible defeaters and considers the likely timing of the intelligence explosion. He also examines the consequences of the intelligence explosion, and how we might constrain a self-improving AI. The final sections of the paper consider the implications of an intelligence explosion for our concepts of consciousness and personal identity.

Goertzel & Pennachin, eds. (2010). Artificial General Intelligence. Springer.

This edited volume begins with a survey of different approaches to artificial general intelligence, and contains contributions from a variety of AGI researchers who summarize their views on how AGI could be achieved.

Good (1965). Speculations concerning the first ultraintelligent machine. Advanced in Computers, 6: 31-88.

Good's paper is the source of the intelligence explosion hypothesis: "Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an intelligence explosion, and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make."

Loosemore & Goertzel (2011). Why an intelligence explosion is probable. H+ Magazine, March 7, 2011.

The authors raise several common objections to the intelligence explosion hypothesis and offer responses to each one in turn.

Sandberg & Bostrom (2008). Whole Brain Emulation: A Roadmap, Technical Report #2008-3. Future of Humanity Institute, Oxford University.

The authors point out that while WBE presents "a formidable engineering and research problem," it seems to be achievable by extrapolations of current technology, unlike other transformative technologies like machine superintelligence, for which we have no metric by which to tell how far we are from the goal. As they see it, the basic idea of WBE is "to take a particular brain, scan its structure in detail, and construct a software model of it that is so faithful to the original that, when run on appropriate hardware, it will behave in essentially the same way as the original brain." They go on to examine different levels of success criteria, challenges, and assumptions of WBE, and present a roadmap for how to get to WBE.

Muehlhauser (2011). Singularity FAQ.

A list of frequently asked questions about the intelligence explosion Singularity, with answers from the Singularity Institute. A quick and handy overview of the major concepts and problems involved.

Vinge (1993). The coming technological singularity: How to survive in the post-human era. Whole Earth Review, winter 1993. New Whole Earth.

Vinge argues that machine superintelligence will arise soon by one of many possible paths, one of which is Good's 'intelligence explosion.' He imagines the benefits that superintelligence coudld bring, as well as the risks of human extinction or slavery. This is the article that seems to have begun wide discussion of the Singularity on the internet, which eventually led to discussions in academia.

Yudkowsky (2008). Artificial Intelligence as Positive and Negative Factor in Global Risk. In Bostrom & Cirkovic, M. (eds.), Global Catastrophic Risks. Oxford University Press.

Yudkowsky explains the risks of machine superintelligence resulting from an intelligence explosion, warning against anthropomorphic bias. He stresses that most possible minds designs for superintelligence will tend toward human extinction, and examines several failure scenarios for the goal of designing 'Friendly AI.' He also examines several strategies for dealing with the threat, and reminds us that despite its risks, superintelligence may also be the only way to mitigate other existential risks.

All Readings (by topic, chronological)

Intelligence Explosion

Good (1965). Speculations concerning the first ultraintelligent machine. Advanced in Computers, 6: 31-88.

Moravec (1989). Mind Children. Harvard University Press.

Vinge (1993). The coming technological singularity: How to survive in the post-human era. Whole Earth Review, winter 1993. New Whole Earth.

Moravec (1999). Robot: Mere Machine to Transcendent Mind. Oxford University Press.

Hibbard (2001). Super-intelligent machines. Computer Graphics, 35(1): 11-13.

Yudkowsky (2001). Staring in to the singularity.

Hibbard (2002). Super-Intelligent Machines. Springer.

Omohundro (2007). The Nature of Self-Improving Artificial Intelligence. Self-Aware Systems.

Yudkowsky (2007). Three major singularity schools.

Legg (2008). Machine super-intelligence. PhD Thesis. IDSIA.

Mahoney (2008). A model for recursively self improving programs.

Omohundro (2008). The Basic AI Drives. Self-Aware Systems.

Yudkowsky (2008). Artificial Intelligence as Positive and Negative Factor in Global Risk. In Bostrom & Cirkovic, M. (eds.), Global Catastrophic Risks. Oxford University Press.

Sandberg (2009). An overview of models of technological singularity.

Smart (2009). Evo Devo Universe? A Framework for Speculations on Cosmic Culture. In Dick & Lupisella (eds.), Cosmos & Culture. NASA Press.

Chalmers (2010). The Singularity: A Philosophical Analysis. Journal of Consciousness Studies, 17: 7-65.

Loosemore & Goertzel (2011). Why an intelligence explosion is probable. H+ Magazine, March 7, 2011.

Muehlhauser (2011). Singularity FAQ.

Technological Forecasting

Solomonoff (1985). The time scale of artificial intelligence: Reflections on social effects. North-Holland Human Systems Management, 5: 149-153.

Bostrom (1998). How long before superintelligence? International Journal of Future Studies, 2.

Moravec (1998). When will computer hardware match the human brain? Journal of Transhumanism, 1.

Kurzweil (1999). The Age of Spiritual Machines: When computers exceed human intelligence. Viking.

Yudkowsky (2001). Staring into the singularity.

Kurzweil (2005). The Singularity is Near. Viking.

Goertzel (2007). Human-level artificial general intelligence and the possibility of a technological singularity. Viking.

Heylighen (2007). Accelerating socio-technological evolution: from ephemeralization and stigmergy to the global brain. In Modelski, Devezas, & Thompson (eds.), Globalization as an Evolutionary Process: Modeling Global Change. Routledge.

Shulman & Sandberg (2010). Implications of a software-limited singularity.

Baum, Goertzel, & Goertzel (2011). How long until human-level AI? Results from an expert assessment. Technological Forecasting and Social Change.

Risks of Intelligence Explosion

Joy (2000). Why the future doesnt need us. Wired 8.04.

Yudkowsky (2000). What is Friendly AI? Singularity Institute.

Hanson (2001). Economic growth given machine intelligence.

Yudkowsky (2001). Staring into the singularity.

Yudkowsky (2001). Creating Friendly AI. Singularity Institute.

Goertzel (2002). Thoughts on AI morality. Dynamical Psychology.

Bostrom (2003). Ethical issues in advanced artificial intelligence. In Smit, Lasker & Wallach (eds.), Cognitive, emotive and ethical aspects of decision making in humans and in arti?cial intelligence, vol II. IIAS, Windsor.

Goertzel (2004). The All-Seeing (A)I. Dynamical Psychology.

Goertzel (2004). Encouraging a positive transcension. Dynamical Psychology.

Yudkowsky (2004). Coherent Extrapolated Volition. Singularity Institute.

de Garis (2005). The Artilect War: Cosmists Vs. Terrans: A Bitter Controversy Concerning Whether Humanity Should Build Godlike Massively Intelligent Machines. ETC Publications.

Hibbard (2005). The ethics and politics of super-intelligent machines.

Posner (2005). Catastrophe: Risk and Response. Oxford University Press.

Weiler (2005). Technological Progress in Different Cultures and Periods: Historical Evolution Projected into the Future. In Wilderer, Schroeder, & Kopp (eds.), Global Sustainability: The Impact of Local Cultures. Wiley.

Armstrong (2007). Chaining God: a qualitative approach to AI, trust and moral systems.

Bugaj & Goertzel (2007). Five ethical imperatives and their implications for human-AGI interaction. Dynamical Psychology.

Hall (2007). Ethics for artificial intellects. In Allhoff, Lin, Moor, & Weckert (eds.), Nanoethics: The ethical and social implications of nanotechnology. Wiley-Interscience.

Hall (2007). Self-improving AI: an analysis. Minds and Machines, 17: 249-259.

Berglas (2009). Artificial intelligence will kill our grandchildren.

Freeman (2009). Using compassion and respect to motivate an artificial intelligence.

Fox & Shulman (2010). Superintelligence does not imply benevolence.

Goertzel (2010a). Coherent aggravated volition: a method for deriving goal system content for advanced, beneficial AGIs.

Goertzel (2010b). GOLEM: Toward an AGI meta-architecture enabling both goal preservation and radical self-improvement.

Hall (2007). Beyond AI: Creating the Conscience of the Machine. Prometheus Books.

Hall (2008). Engineering utopia.

Shulman (2009). Arms control and intelligence explosions.

Shulman, Johnsson, & Tarleton (2009). Machine ethics and superintelligence.

Waser (2008). A safe ethical system for intelligent machines.

Kaas, Rayhawk, Salamon, & Salamon (2010). Economic implications of software minds.

Shulman (2010). Basic AI drives and catastrophic risks.

Sotala (2010). From mostly harmless to civilization-threatening: pathways to dangerous artificial intelligences.

Tarleton (2010). Coherent extrapolated volition: a meta-level approach to machine ethics.

Waser (2010). Designing a safe motivational system for intelligent machines.

Bostrom & Yudkowsky (2011). The ethics of artificial intelligence. In Ramsey & Frankish (eds.), Cambridge Handbook of Artificial Intelligence. Cambridge University Press.

Hall (2011). Ethics for self-improving machines. In Anderson & Anderson (eds.), Machine Ethics (pp. 512-523). Cambridge University Press.

Yudkowsky (2011). Complex value systems in Friendly AI. In Schmidhuber, Thorisson, & Looks (eds.), Artificial General Intelligence, 4th Annual Conference, AGI 2011 (pp. 388-393). Springer.

Armstrong, Sandberg, & Bostrom (2011). Thinking inside the box: Using and controlling an Oracle AI.

Artificial General Intelligence Programming

Goertzel, Pennachin, Senna, Maia, & Lamacie (2004). Novamente: An integrative architecture for artificial general intelligence.

Schmidhuber (2005). Completely self-referential optimal reinforcement learners. ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications, Volume II.

Franklin (2007). A foundational architecture for artificial general intelligence. Proceedings of the 2007 Conference on Advances in Artificial General Intelligence.

Goertzel & Pennachin, eds. (2007). Artificial General Intelligence. Springer. Containing:

• Pennachin & Goertzel. Contemporary approaches to artificial general intelligence.
• Wang. The logic of intelligence.
• Goertzel & Pennachin. The Novamente artificial intelligence engine.
• Voss. Essentials of general intelligence: The direct path to artificial general intelligence.
• de Garis. Artificial brains.
• Schmidhuber. The new AI: General and sound and relevant for physics.
• Schmidhuebr. Godel machines: Fully self-referential optimal universal self-improvers.
• Hutter. Universal algorithmic intelligence: A mathematical top-down approach.
• Kaiser. Program search as a path to artificial general intelligence.
• Red'ko. The natural way to artificial intelligence.
• Hoyes. 3D simulation: The key to AI.
• Yudkowsky. Levels of organization in general intelligence.

Legg & Hutter (2007). A collection of definitions of intelligence.

Ekbia (2008). Artificial Dreams: The Quest for Non-Biological Intelligence. Cambridge University Press.

Wang, Goertzel, & Franklin, eds. (2008). Artificial General Intelligence 2008: Proceedings of the First AGI Conference. IOS Press. Containing:

• Abkasis, Gottlieb, & Itzchaki. Participating in cognition: The interactive search optimization algorithm.
• Achler & Amir. Input feedback networks: Classification and inference based on network structure.
• Arieli. Reasoning with prioritized data by aggregation of distance functions.
• Arieli & Zamansky. Distance-based non-deterministic semantics.
• Arkin. Governing lethal behavior: Embedding ethics in a hybrid deliberative/reactive robot architecture. Part 2: Formalization for ethical control.
• Bach. Seven principles of synthetic intelligence.
• Borzenko. Language processing in human brain.
• Bringsjord, Shilliday, Taylor, Werner, Clark, Charpentier, & Bringsjord. Toward logic-based cognitively robust synthetic characters in digital environments.
• Cassimatis, Murugesan, & Bugajska. A cognitive substrate for natural language understanding.
• de Garis, Tang, Huang, Bai, Chen, Chen, Guo, Tan, Tian, Tian, Wu, Xiong, Yu, & Huang. The China-brain project: Building China's artificial brain using an evolved neural net module approach.
• Duch, Oentaryo, & Pasquier. Cognitive architectures: Where do we go from here?
• Friedlander & Franklin. LIDA and a theory of mind.
• Goertzel & Pennachin. How might probabilistic reasoning emerge from the brain?
• Goerztel, Pennachin, Geissweiller, Looks, Senna, Silva, Heljakka, & Lopes. An integrative methodology for teaching embodied non-linguistic agents, applied to virtual animals in Second Life.
• Hall. VARIAC: An autogenous cognitive architecture.
• Ikle & Goertzel. Probabilistic quantifier logic for general intelligence: An indefinite probabilities approach.
• Johnston & Williams. Comirit: Commonsense reasoning by integrating simulation and logic.
• Kuhnberger, Geibel, Gust, Krumnack, Ovchinnikova, Schwering, & Wandmacher. Learning from inconsistencies in an integrated cognitive architecture.
• Laird. Extending the Soar cognitive architecture.
• Magnusson & Doherty. Temporal action logic for question answering in an adventure game.
• Milch. Artificial general intelligence through large-scale, multimodal Bayesian learning.
• Pankov. A computational approximation to the AIXI model.
• Pickett, Miner, & Oates. Essential phenomena of general intelligence.
• Pollack. OSCAR: An architecture for generally intelligent agents.
• Quinton, Buisson & Perotto. Anticipative coordinated cognitive processes for interactivist and Piagetian theories.
• Recanati. Hybrid reasoning and the future of iconic representations.
• Samsonovich, de Jong, Kitsantas, Peters, Dabbagh, & Kalbfleisch. Cognitive constructor: An intelligent tutoring system based on a biologically inspired cognitive architecture (BICA).
• Taylor, Kuhlmann, & Stone. Transfer learning and intelligence: An argument and approach.
• Tripodes. Real time machine deduction and AGI.
• Voskresenskij. Text disambiguation by educable AI system.
• Wang. What do you mean by 'AI'?
• Zadeh, Shouraki, & Halavati. Using decision trees to model an emotional attention mechanism.
• Connell. Fusing animals and humans.
• Connell & Livingston. Four paths to AI.
• Hibbard. Adversarial sequence prediction.
• Hwang, Hwang, & Hwang. Artificial general intelligence via finite covering and learning.
• Iyengar. Cognitive primitives for automated learning.
• Levy & Gayler. Vector symbolic architectures: A new building material for artificial general intelligence.
• Schwering, Krumnack, Kuhnberger, & Gust. Analogy as integrating framework for human-level reasoning.
• Sharma. Designing knowledge based systems as complex adaptive systems.
• Smith. Artificial general intelligence: An organism and level based position statement.
• de Garis. The artilect war: Cosmists vs. Terrans. A bitter controversy concerning whether humanity should build godlike massively intelligent machines.
• Goertzel & Bugaj. Stages of ethical development in artificial general intelligence systems.
• Hall. Engineering utopia.
• Hart & Goertzel. OpenCog: A software framework for integrative artificial general intelligence.
• Hibbard. Open source AI.
• Livingston, Garvey, & Elhanany. On the broad implications of reinforcement learning based AGI.
• Omohundro. The Basic AI Drives.
• Samsonovich, Ascoli, Morowitz, & Kalbfleisch. A scientific perspective on the hard problem of consciousness.

Mahoney (2008). A proposed design for distributed artificial general intelligence.

Goertzel, Hitzler, & Hutter (2009). Proceedings of the Second Conference on Artificial General Intelligence. Atlantis Press. Containing:

• Baum. How to build programs that understand.
• Bittle & Fox. CHS-Soar: Introducing constrained heuristic search to the Soar cognitive architecture.
• Chella & Gaglio. In search of computational correlates of artificial qualia.
• Crossley, Kitzelmann, Hofmann, & Schmid. Combining analytical and evolutionary inductive programming.
• de Garis: The China-Brain project: Report on the first six months.
• Goertzel & Bugaj. AGI Preschool: A framework for evaluating early-stage human-like AGIs.
• Ghosh, Lowe, & Saraf. Pointer semantics with forward propogation.
• Gust, Krumnack, Schwering, & Kuehnberger. The role of logic in AGI systems: Towards a lingua franca for general intelligence.
• Hall. The robotics path to AGI using servo stacks.
• Hofmann, Kitzelmann, & Schmid. A unifying framework for analysis and evaluation of inductive programming systems.
• Hutter. Feature Markov decision processes.
• Hutter. Feature dynamic Bayesian networks.
• Ikle, Pitt, Goertzel, & Sellman. Economic attention networks: Associative memory and resource allocation for general intelligence.
• Johnston & Williams. A formal framework for the symbol grounding problem.
• Kurup & Chandrasekaran. A cognitive map for an artificial agent.
• Laird, Wray, Marinier, & Langley. Claims and challenges in evaluating human-level intelligent systems.
• Lathrop & Laird. Extending cognitive architectures with mental imagery.
• Lebiere, Gonzalez, & Warwick. A comparative approach to understanding general intelligence: Predicting cognitive performance in an open-ended dynamic task.
• Liu & Schubert. Incorporating planning and reasoning into a self-motivated, communicative agent.
• Looks & Goertzel. Problem representation for general intelligence.
• Loosemore. Consciousness in human and machine: A theory and some falsifiable predictions.
• Lorincz. Hebbian constraint on the resolution of the homunculus fallacy leads to a network that searches for hidden cause-effect relationships.
• MacInnes, Armstrong, Pare, Cree, & Joordens. Everyone's a critic: Memory models and uses for an artificial Turing judge.
• Miller, Wong, & Stoytchev. Unsupervised segmentation of audio speech using the voting experts algorithm.
• Murugesan & Cassimatis. Parsing PCFG within a general probabilistic inference framework.
• Nivel & Thorisson. Self-programming: Operationalizing autonomy.
• Reed. Bootstrap dialog: A conversational English text parsing and generation system.
• Schmid, Hofmann, & Kitzelmann. Analytical inductive programming as a cognitive rule acquisition device.
• Tripodes. Human and machine understanding of natural language character strings.
• Wang. Embodiment: Does a laptop have a body?
• Wang. Case-by-case problem solving.
• Waser. What is artificial general intelligence? Clarifying the goal for engineering and evaluation.
• Wintermute. Integrating action and reasoning through simulation.
• Achler & Amir. Neuroscience and AI share the same elegant mathematical trap.
• Baum. Relevance based planning: Why it's a core process for AGI.
• Bringsjord. General intelligence and hypercomputation.
• Gros. Stimulus processing in autonomously active cognitive systems.
• Hibbard. Distribution of environments in formal measures of intelligence.
• Hitzler & Kuhnberger. The importance of being neural-symbolic: A Wilde position.
• Miles & Tashakkori. Improving the believability of non-player characters in simulations.
• Miner, Pickett, & desJardins. Understanding the brain's emergent properties.
• Samsonovich. Why BICA is necessary for AGI.
• Surowitz. Importing space-time concepts into AGI.
• Swaine. HELEN: Using brain regions and mechanisms for story understanding and modeling language as human behavior.
• Thorisson & Nivel. Holistic intelligence: Transversal skills and current methodologies.
• Thorisson & Nivel. Achieving artificial general intelligence through peewee granularity.

Goertzel (2009). OpenCogPrime: A cognitive synergy based architecture for artificial general intelligence. 8th IEEE International Conference on Cognitive Information.

Goertzel, Arel, & Scheutz (2009). Toward a roadmap for human-level artificial general intelligence: Embedding HLAI systems in broad, approachable, physical or virtual contexts.

Lebiere, Gonzalez, & Warwick (2009). A comparative approach to understanding general intelligence: Predicing cognitive performance in an open-ended dynamic task. Department of Social and Decision Sciences, Paper 82. Carnegie Mellon University.

Schmidhuber (2009). Ultimate cognition a la Godel. Cognitive Computation, 1: 177-193.

Baum, Hutter, & Kitzelmann, eds. (2010). Proceedings of the Third Conference on Artificial General Intelligence. Atlantis Press. Containing:

• Bignoli, Cassimatis, & Murugesan. Efficient constraint-satisfaction in domains with time.
• Gobet & Lane. The CHREST architecture of cognition: The role of perception in general intelligence.
• Goertzel, Pennachin, Araujo, Lian, Silva, Wueiroz, Silva, Ross, Vepstas, & Senna. A general intelligence oriented architecture for embodied natural language processing.
• Goertzel. Toward a formal characterization of real-world general intelligence.
• Hernandez-Orallo. On evaluating agent performance in a fixed period of time.
• Hewlett & Cohen. Artificial general segmentation.
• Ilke & Goertzel. Grounding possible world semantics in experiential semantics.
• Johnson. The toy box program (and a preliminary solution).
• Kaiser & Stafiniak. Playing general structure rewriting games.
• Kerr, Nehmzow, & Billings. Towards automated code generation for autonomous mobile robots.
• Koutnik, Gomez, & Schmidhuber. Searching for minimal neural networks in Fourier space.
• Krumnack, Gust, Schwering, & Kuehnberger. Remarks on the meaning of analogical relations.
• Kurup & Cassimatis. Quantitative spatial reasoning for general intelligence.
• Laird & Wray. Cognitive architecture requirements for achieving AGI.
• Lorincz, Bardosi, & Takacs. Sketch of an AGI architecture with illustration.
• Maei & Sutton. GQ(λ): A general gradient algorithm for temporal-difference prediction learning with eligibility traces.
• Memon & Treur. A generic adaptive agent architecture integrating cognitive and affective states and their interaction.
• Ng, Tan, Teow, Ng, Tan, & Chan. A cognitive architecture for knowledge exploitation.
• Nan & Costello. An artificial intelligence model that combines spatial and temporal perception.
• Ortega & Braun. A conversion between utility and information.
• Ortega & Braun. A Bayesian rule for adaptive control based on causal interventions.
• Ray & Oates. Discovering and characterizing hidden variables.
• Rohrer. What we might look for in an AGI benchmark.
• Schaul & Schmidhuber. Towards a practical universal search.
• Schmidhuber. Artificial scientists and artists based on the formal theory of creativity.
• Solomonoff. Algorithmic probability, heuristic programming and AGI.
• Sun, Glasmachers, Schaul, & Schmidhuber. Frontier search.
• Wang. The evaluation of AGI systems.
• Waser. Designing a safe motivational system for intelligent machines.
• Chella, Cossentino, & Seidita. Software design of an AGI system based on perception loop.
• Demasi, Szwarcfiter, & Cruz. A theoretical framework to formalize AGI-hard problems.
• Geisweiller & Goertzel. Uncertain spatiotemporal logic for general intelligence.
• Hernandez-Orallo. A (hopefully) unbiased universal environment class for measuring intelligence of biological and artificial systems.
• Kim. Neuroethological approach to understanding intelligence.
• Looks. Compression progress, pseudorandomness, and hyperbolic discounting.
• Orseau. Relational local iterative compression.
• Ozkural & Aykanat. Stochastic grammar based incremental machine learning using scheme.
• Pape. Compression-driven progress in science.
• Thomsen. Concept formation in the Ouroboros model.
• Wiedermann. On super-Turing computing power and heirarchies of artificial general intelligence systems.
• de Ven & Schouten. A minimum relative entropy principle for AGI.

Gluck, Stanley, Moore, Reitter, & Halbrugge (2010). Exploration for understanding in cognitive modeling. Journal of Artificial General Intelligence, 2(2): 88-107.

Lebiere, Gonzalez, & Warwick (2010). Cognitive architectures, model comparison, and AGI. Journal of Artificial General Intelligence, 2(2): 1-19.

Myers, Gluck, Gunzelmann, & Krusmark (2010). Validating computational cognitive process models across multiple timescales. Journal of Artificial General Intelligence, 2(2): 108-127.

Peebles & Banks (2010). Modelling dynamic decision makers with the ACT-R cognitive architecture. Journal of Artificial General Intelligence, 2(2): 52-68.

Reitter (2010). Metacognition and multiple strategies in a cognitive model of online control. Journal of Artificial General Intelligence, 2(2): 20-37.

Rohrer (2010). Accelerating progress in artificial general intelligence: Choosing a benchmark for natural world interaction. Journal of Artificial General Intelligence, 2(1): 1-28.

Stewart & West (2010). Testing for equivalence: A methodology for computational cognitive modelling. Journal of Artificial General Intelligence, 2(2): 69-87.

Hernandez-Orallo, Dowe, Espana-Cubillo, Hernandez-Lloreda, & Insa-Cabrera (2011). On more realistic environment distributions for defining, evaluating and developing intelligence. Artificial General Intelligence.

Schmidhuber, Thorisson, & Looks, eds. (2011). Artificial General Intelligence: 4th International Conference, AGI 2011. Springer. Containing:

• Orseau & Ring. Self-modification and mortality in artificial agents.
• Ring & Orseau. Delusion, survival, and intelligent agents.
• Schaul, Pape, Tlasmachers, Graziano, & Schmidhuber. Coherence progress: A measure of interestingness based on fixed compressors.
• Gisslen, Luciw, Graziano, & Schmidhuber. Sequential constant size compressors for reinforcement learning.
• Sun, Gomez, & Schmidhuber. Planning to be surprised: Optimal Bayesian exploration in dynamic environments.
• Glasmachers & Schmidhuber. Optimal direct policy search.
• Ikle & Goertzel. Nonlinear-Dynamical attention allocation via information geometry.
• Epstein & Betke. An information theoretic representation of agent dynamics as set interactions.
• Hernandez-Orallo, Dowe, Espana-Cubillo, Hernandez-Lloreda, & Insa-Cabrera. On more realistic environment distributions for defining, evaluating, and developing intelligence.
• Pissanetzky. Structural emergence in partially ordered sets is the key to intelligence.
• Kurup, Lebiere, & Stentz. Integrating perception and cognition for AGI.
• Monner & Reggia. Systematically grounding language through vision in a deep, recurrent neural network.
• Insa-Cabrera, Dowe, Espana-Cubillo, Hernandez-Lloreda, & Hernandez-Orallo. Comparing humans and AI agents.
• Snaider, McCall, & Frankling. The LIDA framework as a general tool for AGI.
• Rosenbloom. From memory to problem solving: Mechanism reuse in a graphical cognitive architecture.
• Waser. Rational universal benevolence: Simpler, safer, and wiser than "Friendly AI".
• Johnston. The collection of physical knowledge and its application in intelligent systems.
• Gust, Krumnack, Martinez, Abdel-Fattah, Schmidt, & Kuhnberger. Rationality and general intelligence.
• Popescu. Wagging the dog: Human vs. machine inference of causality in visual sequences.
• Dindo, Chella, La Tona, Vitali, Nivel, & Thorisson. Learning problem solving skills from demonstration: An architectural approach.
• Dowe, Hernandez-Orallo, & Das. Compression and intelligence: Social environments and communication.
• Cai, Goertzel, & Geisweiller. OpenPsi: Realizing Dorner's "Psi" cognitive model in OpenCog integrative AGI architecture.
• Oltramari & Lebiere. Extending cognitive architectures with semantic resources.
• Bach. Motivational system for cognitive AI.
• Schmidhuber, Ciresan, Meier, Masci, & Graves. On fast deep nets for AGI vision.
• Thill. Considerations for a neuroscience-inspired approach to the design of artificial intelligent systems.
• Coward. Brain anatomy and artificial intelligence.
• Ortega & Braun. Information, utility, and bounded rationality.
• Steunebrink & Schmidhuber. A family of Godel machine implementations.
• Ortega, Braun, & Godsill. Reinforcement learning and the Bayesian control rule.
• Hibbard. Societies of intelligent agents.
• Ruiz, Melendez, & Sucar. Towards a general vision system based on symbol-relation grammars and Bayesian networks.
• Wang & Awan. Reasoning in non-axiomatic logic: A case study in medical diagnosis.
• Hibbard. Measuring agent intelligence via heirarchies of environments.
• Dewey. Learning what to value.
• Lorincz. Learning the states: A brain inspired neural model.
• Lorincz & Takacs. AGI architecture measures human parameters and optimizes human performance.
• Waledzik & Mandziuk. Multigame playing by means of UCT enhanced with automatically generated evaluation functions.
• Raab, Wernsdorfer, Kitzelmann, & Schmid. From sensorimotor graphs to rules: An agent learns from a stream of experience.
• Goertzel & Ikle. Three hypotheses about the geometry of mind.
• Goertzel. Imprecise probability as a linking mechanism between deep learning, symbolic cognition and local feature detection in visual processing.
• Mingus, Kriete, Herd, Wyatte, Latimer, & O'Reilly. Generalization of figure-ground segmentation from binocular to monocular vision in an embodied biological brain model.
• Touzet. The illusion of internal joy.
• Oved & Fasel. Philosophically inspired concept acquisition for artificial general intelligence.
• Silver. Machine lifelong learning: Challenges and benefits for artificial general intelligence.
• Nan & Costello. A demonstration of combining spatial and temporal perception.
• Ozkural. Towards heuristic algorithmic memory.
• Yudkowsky. Complex value systems in Friendly AI.
• Pape & Kok. Real-world limits to algorithmic intelligence.
• Koene. AGI and neuroscience: Open sourcing the brain.
• Szary, Kerster, & Kello. What makes a brain smart? Reservoir computing as an approach for general intelligence.

Whole Brain Emulation

Martin (1971). Brief proposal on immortality: an interim solution. Perspectives in Biology and Medicine, 14: 339.

Moravec (1989). Mind Children. Harvard University Press.

Hanson (1994). If uploads come first: The crack of a future dawn. Extropy, 6(2): 1015.

Moravec (1999). Robot: Mere Machine to Transcendent Mind. Oxford University Press.

Yudkowsky (2001). Staring into the singularity.

Markram (2006). The Blue Brain Project. Nature Reviews Neuroscience, 7: 153-160.

Leitl (2007). Neurosuspension and uploading.

Malickas (2007). Gradual uploading as a cognition of mind.

Plesser, Eppler, Morrison, Diesmann, & Gewaltig (2007). Efficient parallel simulation of large-scale neuronal networks on clusters of multiprocessor computers. Lecture Notes in Computer Science, 4641: 672-681.

Hanson (2008). Economics of brain emulations. In Healey & Rayner (eds.), Unnatural Selection: The Challenges of Engineering Tomorrow's People. EarthScan.

Hanson (2008). Economics of the singularity. IEEE Spectrum.

Hines, Markram, & Schurmann (2008). Fully implicit parallel simulation of single neurons. Journal of Computational Neuroscience, 25: 439-448.

Sandberg & Bostrom (2008). Whole Brain Emulation: A Roadmap, Technical Report #2008?3. Future of Humanity Institute, Oxford University.

Yudkowsky (2008). Artificial Intelligence as Positive and Negative Factor in Global Risk. In Bostrom & Cirkovic, M. (eds.), Global Catastrophic Risks. Oxford University Press.

Asanthanarayan, Esser, Simon, & Modha (2009). The cat is out of the bag: Cortical simulations with 10⁹ neurons, 10¹³ synapses. Proceedings of the Conference on High Performance Computing, Networking, Storage, and Analysis.

Astakhov (2010). Continuum of consciousness: mind uploading and resurrection of human consciousness.

Borzenko (2010). Indirect mind upload.

Cattell & Parker (2010). Challenges for whole brain emulation: Why is building a brain so difficult?

Shulman (2010). Whole brain emulation and the evolution of superorganisms. Singularity Institute.

If you have any corrections or additions for this bibliography, please contact the editor: luke [at] singinst [dot] org.

Subscribe for updates on research about the intelligence explosion:

IntelligenceExplosion.com is maintained by the Singularity Institute.