SpringerLink
Log in

AIXI, FEP-AI, and Integrated World Models: Towards a Unified Understanding of Intelligence and Consciousness

  • Conference paper
  • First Online:
Active Inference (IWAI 2022)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1721))

Included in the following conference series:

Abstract

Intelligence has been operationalized as both goal-pursuit capacity across a broad range of environments, and also as learning capacity above and beyond a foundational set of core priors. Within the normative framework of AIXI, intelligence may be understood as capacities for compressing (and thereby predicting) data and achieving goals via programs with minimal algorithmic complexity. Within the Free Energy Principle and Active Inference framework, intelligence may be understood as capacity for inference and learning of predictive models for goal-realization, with beliefs favored to the extent they fit novel data with minimal updating of priors. Most recently, consciousness has been proposed to enhance intelligent functioning by allowing for iterative state estimation of the essential variables of a system and its relationships to its environment, conditioned on a causal world model. This paper discusses machine learning architectures and principles by which all these views may be synergistically combined and contextualized with an Integrated World Modeling Theory of consciousness.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Safron, A.: An integrated world modeling theory (IWMT) of consciousness: combining integrated information and global neuronal workspace theories with the free energy principle and active inference framework; toward solving the hard problem and characterizing agentic causation. Front. Artif. Intell. 3 (2020). https://doi.org/10.3389/frai.2020.00030

  2. Safron, A.: Integrated world modeling theory (IWMT) implemented: towards reverse engineering consciousness with the free energy principle and active inference. PsyAr**v (2020). https://doi.org/10.31234/osf.io/paz5j

  3. Greff, K., van Steenkiste, S., Schmidhuber, J.: On the binding problem in artificial neural networks. ar**v:2012.05208 [cs] (2020)

  4. Evans, R., Hernández-Orallo, J., Welbl, J., Kohli, P., Sergot, M.: Making sense of sensory input. Artif. Intell. 293, 103438 (2021). https://doi.org/10.1016/j.artint.2020.103438

    Article  MathSciNet  MATH  Google Scholar 

  5. De Kock, L.: Helmholtz’s Kant revisited (Once more). The all-pervasive nature of Helmholtz’s struggle with Kant’s Anschauung. Stud. Hist. Philos. Sci. 56, 20–32 (2016). https://doi.org/10.1016/j.shpsa.2015.10.009

    Article  Google Scholar 

  6. Northoff, G.: Immanuel Kant’s mind and the brain’s resting state. Trends Cogn. Sci. (Regul. Ed.) 16, 356–359 (2012). https://doi.org/10.1016/j.tics.2012.06.001

    Article  Google Scholar 

  7. Swanson, L.R.: The predictive processing paradigm has roots in Kant. Front. Syst. Neurosci. 10, 79 (2016). https://doi.org/10.3389/fnsys.2016.00079

    Article  Google Scholar 

  8. Marcus, G.: The Next decade in AI: four steps towards robust artificial intelligence. ar**v:2002.06177 [cs] (2020)

  9. Safron, A.: The radically embodied conscious cybernetic Bayesian brain: from free energy to free will and back again. Entropy 23, 783 (2021). https://doi.org/10.3390/e23060783

    Article  Google Scholar 

  10. Safron, A., Çatal, O., Verbelen, T.: Generalized simultaneous localization and map** (G-SLAM) as unification framework for natural and artificial intelligences: towards reverse engineering the hippocampal/entorhinal system and principles of high-level cognition (2021). https://psyarxiv.com/tdw82/, https://doi.org/10.31234/osf.io/tdw82

  11. Safron, A., Sheikhbahaee, Z.: Dream to explore: 5-HT2a as adaptive temperature parameter for sophisticated affective inference (2021). https://psyarxiv.com/zmpaq/, https://doi.org/10.31234/osf.io/zmpaq

  12. Safron, A.: On the Varieties of conscious experiences: altered beliefs under psychedelics (ALBUS) (2020). https://psyarxiv.com/zqh4b/, https://doi.org/10.31234/osf.io/zqh4b

  13. Schmidhuber, J.: Planning & reinforcement learning with recurrent world models and artificial curiosity (1990). https://people.idsia.ch//~juergen/world-models-planning-curiosity-fki-1990.html. Accessed 16 May 2021

  14. Schmidhuber, J.: First very deep learning with unsupervised pre-training (1991). https://people.idsia.ch//~juergen/very-deep-learning-1991.html. Accessed 16 May 2021

  15. Schmidhuber, J.: Making the world differentiable: on using self-supervised fully recurrent neural networks for dynamic reinforcement learning and planning in non-stationary environments (1990)

    Google Scholar 

  16. Schmidhuber, J.: Neural sequence chunkers (1991)

    Google Scholar 

  17. Schmidhuber, J.: Learning complex, extended sequences using the principle of history compression. Neural Comput. 4, 234–242 (1992). https://doi.org/10.1162/neco.1992.4.2.234

    Article  Google Scholar 

  18. Schmidhuber, J.: Algorithmic theories of everything (2000). ar**v:quant-ph/0011122

  19. Schmidhuber, J.: The speed prior: a new simplicity measure yielding near-optimal computable predictions. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 216–228. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-45435-7_15

    Chapter  Google Scholar 

  20. Schmidhuber, J.: Gödel machines: fully self-referential optimal universal self-improvers. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence, pp. 199–226. Springer, Heidelberg (2007). https://doi.org/10.1007/3-540-45435-7_15

    Chapter  Google Scholar 

  21. Schmidhuber, J.: Simple algorithmic principles of discovery, subjective beauty, selective attention, curiosity & creativity. ar**v:0709.0674 [cs] (2007)

  22. Schmidhuber, J.: POWERPLAY: training an increasingly general problem solver by continually searching for the simplest still unsolvable problem. ar**v:1112.5309 [cs] (2012)

  23. Schmidhuber, J.: On learning to think: algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models. ar**v:1511.09249 [cs] (2015)

  24. Schmidhuber, J.: One big net for everything. ar**v:1802.08864 [cs] (2018)

  25. Kolmogorov, A.N.: On tables of random numbers. Sankhyā: Indian J. Stat. Ser. A (1961–2002) 25, 369–376 (1963)

    Google Scholar 

  26. Schmidhuber, J.: Hierarchies of generalized kolmogorov complexities and nonenumerable universal measures computable in the limit. Int. J. Found. Comput. Sci. 13, 587–612 (2002). https://doi.org/10.1142/S0129054102001291

    Article  MathSciNet  MATH  Google Scholar 

  27. Hutter, M.: A Theory of universal artificial intelligence based on algorithmic complexity. ar**v:cs/0004001 (2000)

    Google Scholar 

  28. Solomonoff, R.J.: Algorithmic probability: theory and applications. In: Emmert-Streib, F., Dehmer, M. (eds.) Information Theory and Statistical Learning, pp. 1–23. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-84816-7_1

  29. Feynman, R.P.: Quantum Mechanics and Path Integrals. McGraw-Hill, New York (1965)

    MATH  Google Scholar 

  30. Kaila, V., Annila, A.: Natural selection for least action. Proc. Roy. Soc. A: Math. Phys. Eng. Sci. 464, 3055–3070 (2008). https://doi.org/10.1098/rspa.2008.0178

    Article  MathSciNet  MATH  Google Scholar 

  31. Campbell, J.O.: Universal darwinism as a process of Bayesian inference. Front. Syst. Neurosci. 10, 49 (2016). https://doi.org/10.3389/fnsys.2016.00049

    Article  Google Scholar 

  32. Vanchurin, V.: The world as a neural network. Entropy 22, 1210 (2020). https://doi.org/10.3390/e22111210

    Article  MathSciNet  Google Scholar 

  33. Hanson, S.J.: A stochastic version of the delta rule. Phys. D 42, 265–272 (1990). https://doi.org/10.1016/0167-2789(90)90081-Y

    Article  Google Scholar 

  34. Orseau, L., Lattimore, T., Hutter, M.: Universal knowledge-seeking agents for stochastic environments. In: Jain, S., Munos, R., Stephan, F., Zeugmann, T. (eds.) ALT 2013. LNCS (LNAI), vol. 8139, pp. 158–172. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40935-6_12

    Chapter  Google Scholar 

  35. Friston, K.J., Lin, M., Frith, C.D., Pezzulo, G., Hobson, J.A., Ondobaka, S.: Active inference, curiosity and insight. Neural Comput. 29, 2633–2683 (2017). https://doi.org/10.1162/neco_a_00999

    Article  MathSciNet  MATH  Google Scholar 

  36. Aslanides, J., Leike, J., Hutter, M.: Universal reinforcement learning algorithms: survey and experiments. ar**v:1705.10557 [cs] (2017)

  37. Friston, K., Da Costa, L., Hafner, D., Hesp, C., Parr, T.: Sophisticated inference (2020)

    Google Scholar 

  38. VanRullen, R., Kanai, R.: Deep learning and the global workspace theory. Trends Neurosci. (2021). https://doi.org/10.1016/j.tins.2021.04.005

  39. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350, 1332–1338 (2015). https://doi.org/10.1126/science.aab3050

    Article  MathSciNet  MATH  Google Scholar 

  40. Lázaro-Gredilla, M., Lin, D., Guntupalli, J.S., George, D.: Beyond imitation: zero-shot task transfer on robots by learning concepts as cognitive programs. Sci. Robot. 4 (2019). https://doi.org/10.1126/scirobotics.aav3150

  41. Ullman, T.D., Tenenbaum, J.B.: Bayesian models of conceptual development: learning as building models of the world. Annu. Rev. Dev. Psychol. 2, 533–558 (2020). https://doi.org/10.1146/annurev-devpsych-121318-084833

    Article  Google Scholar 

  42. Veness, J., Ng, K.S., Hutter, M., Uther, W., Silver, D.: A Monte Carlo AIXI approximation. ar**v:0909.0801 [cs, math] (2010)

  43. Hesp, C., Tschantz, A., Millidge, B., Ramstead, M., Friston, K., Smith, R.: Sophisticated affective inference: simulating anticipatory affective dynamics of imagining future events. In: Verbelen, T., Lanillos, P., Buckley, C.L., De Boom, C. (eds.) IWAI 2020. Communications in Computer and Information Science, vol. 1326, pp. 179–186. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64919-7_18

    Chapter  Google Scholar 

  44. de Abril, I.M., Kanai, R.: A unified strategy for implementing curiosity and empowerment driven reinforcement learning. ar**v:1806.06505 [cs] (2018)

  45. Hafner, D., Lillicrap, T., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. ar**v:1912.01603 [cs] (2020)

  46. Hafner, D., Ortega, P.A., Ba, J., Parr, T., Friston, K., Heess, N.: Action and perception as divergence minimization. ar**v:2009.01791 [cs, math, stat] (2020)

  47. Wang, R., et al.: Enhanced POET: open-ended reinforcement learning through unbounded invention of learning challenges and their solutions. ar**v:2003.08536 [cs] (2020)

  48. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  49. Lee-Thorp, J., Ainslie, J., Eckstein, I., Ontanon, S.: FNet: mixing tokens with fourier transforms. ar**v:2105.03824 [cs] (2021)

  50. Ramsauer, H., et al.: Hopfield networks is all you need. ar**v:2008.02217 [cs, stat] (2021)

  51. Schlag, I., Irie, K., Schmidhuber, J.: Linear transformers are secretly fast weight memory systems. ar**v:2102.11174 [cs] (2021)

  52. Tay, Y., et al.: Are pre-trained convolutions better than pre-trained transformers? ar**v:2105.03322 [cs] (2021)

  53. Hawkins, J., Ahmad, S.: Why neurons have thousands of synapses, a theory of sequence memory in neocortex. Front. Neural Circ. 10 (2016). https://doi.org/10.3389/fncir.2016.00023

  54. Knight, R.T., Grabowecky, M.: Escape from linear time: prefrontal cortex and conscious experience. In: The Cognitive Neurosciences, pp. 1357–1371. The MIT Press, Cambridge (1995)

    Google Scholar 

  55. Koster, R., et al.: Big-loop recurrence within the hippocampal system supports integration of information across episodes. Neuron 99, 1342-1354.e6 (2018). https://doi.org/10.1016/j.neuron.2018.08.009

    Article  Google Scholar 

  56. Faul, L., St. Jacques, P.L., DeRosa, J.T., Parikh, N., De Brigard, F.: Differential contribution of anterior and posterior midline regions during mental simulation of counterfactual and perspective shifts in autobiographical memories. NeuroImage. 215, 116843 (2020). https://doi.org/10.1016/j.neuroimage.2020.116843

  57. Mannella, F., Gurney, K., Baldassarre, G.: The nucleus accumbens as a nexus between values and goals in goal-directed behavior: a review and a new hypothesis. Front. Behav. Neurosci. 7, 135 (2013). https://doi.org/10.3389/fnbeh.2013.00135

    Article  Google Scholar 

  58. Friston, K.J., FitzGerald, T., Rigoli, F., Schwartenbeck, P., Pezzulo, G.: Active inference: a process theory. Neural Comput. 29, 1–49 (2017). https://doi.org/10.1162/NECO_a_00912

    Article  MathSciNet  MATH  Google Scholar 

  59. Friston, K.J.: am i self-conscious? (Or does self-organization entail self-consciousness?). Front. Psychol. 9 (2018). https://doi.org/10.3389/fpsyg.2018.00579

  60. Ha, D., Schmidhuber, J.: World models. ar**v:1803.10122 [cs, stat] (2018). https://doi.org/10.5281/zenodo.1207631

  61. Rusu, S.I., Pennartz, C.M.A.: Learning, memory and consolidation mechanisms for behavioral control in hierarchically organized cortico-basal ganglia systems. Hippocampus 30, 73–98 (2020). https://doi.org/10.1002/hipo.23167

    Article  Google Scholar 

  62. Sanders, H., Wilson, M.A., Gershman, S.J.: Hippocampal remap** as hidden state inference. eLife. 9, e51140 (2020). https://doi.org/10.7554/eLife.51140

  63. Hoel, E.: The overfitted brain: dreams evolved to assist generalization. Patterns 2, 100244 (2021). https://doi.org/10.1016/j.patter.2021.100244

    Article  Google Scholar 

  64. Boureau, Y.-L., Dayan, P.: Opponency revisited: competition and cooperation between dopamine and serotonin. Neuropsychopharmacology 36, 74–97 (2011). https://doi.org/10.1038/npp.2010.151

    Article  Google Scholar 

  65. Hassabis, D., Maguire, E.A.: The construction system of the brain. Philos. Trans. R. Soc. London B Biol. Sci. 364, 1263–1271 (2009). https://doi.org/10.1098/rstb.2008.0296

  66. Çatal, O., Verbelen, T., Van de Maele, T., Dhoedt, B., Safron, A.: Robot navigation as hierarchical active inference. Neural Netw. 142, 192–204 (2021). https://doi.org/10.1016/j.neunet.2021.05.010

    Article  Google Scholar 

  67. Schmidhuber, J.H., Mozer, M.C., Prelinger, D.: Continuous history compression. In: Proceedings of International Workshop on Neural Networks, RWTH Aachen, pp. 87–95. Augustinus (1993)

    Google Scholar 

  68. Shine, J.M.: The thalamus integrates the macrosystems of the brain to facilitate complex, adaptive brain network dynamics. Prog. Neurobiol. 199, 101951 (2021). https://doi.org/10.1016/j.pneurobio.2020.101951

    Article  Google Scholar 

  69. Friston, K.J., Parr, T., de Vries, B.: The graphical brain: Belief propagation and active inference. Netw. Neurosci. 1, 381–414 (2017). https://doi.org/10.1162/NETN_a_00018

    Article  Google Scholar 

  70. Parr, T., Friston, K.J.: The discrete and continuous brain: from decisions to movement-and back again. Neural Comput. 30, 2319–2347 (2018). https://doi.org/10.1162/neco_a_01102

    Article  MathSciNet  MATH  Google Scholar 

  71. Gershman, S., Goodman, N.: Amortized inference in probabilistic reasoning. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 36 (2014)

    Google Scholar 

  72. Sales, A.C., Friston, K.J., Jones, M.W., Pickering, A.E., Moran, R.J.: Locus coeruleus tracking of prediction errors optimises cognitive flexibility: an active inference model. PLoS Comput. Biol. 15, e1006267 (2019). https://doi.org/10.1371/journal.pcbi.1006267

    Article  Google Scholar 

  73. Shea, N., Frith, C.D.: The global workspace needs metacognition. Trends Cogn. Sci. (2019). https://doi.org/10.1016/j.tics.2019.04.007

  74. Shine, J.: Neuromodulatory influences on integration and segregation in the brain. Undefined (2019)

    Google Scholar 

  75. Holroyd, C.B., Verguts, T.: The best laid plans: computational principles of anterior cingulate cortex. Trends Cogn. Sci. 25, 316–329 (2021). https://doi.org/10.1016/j.tics.2021.01.008

    Article  Google Scholar 

  76. Carmichael, J.: Artificial intelligence gained consciousness in 1991. https://www.inverse.com/article/25521-juergen-schmidhuber-ai-consciousness. Accessed 14 Nov 2021

  77. Dreyfus, H.L.: Why Heideggerian AI failed and how fixing it would require making it more Heideggerian. Philos. Psychol. 20, 247–268 (2007). https://doi.org/10.1080/09515080701239510

    Article  Google Scholar 

  78. Cisek, P.: Cortical mechanisms of action selection: the affordance competition hypothesis. Philos. Trans. R. Soc. Lond. B Biol. Sci. 362, 1585–1599 (2007). https://doi.org/10.1098/rstb.2007.2054

    Article  Google Scholar 

  79. Seth, A.K.: The cybernetic Bayesian brain. Open MIND. MIND Group, Frankfurt am Main (2014). https://doi.org/10.15502/9783958570108

  80. Tani, J.: Exploring Robotic Minds: Actions, Symbols, and Consciousness as Self-organizing Dynamic Phenomena. Oxford University Press (2016)

    Google Scholar 

  81. Kiverstein, J., Miller, M., Rietveld, E.: The feeling of grip: novelty, error dynamics, and the predictive brain. Synthese 196(7), 2847–2869 (2017). https://doi.org/10.1007/s11229-017-1583-9

    Article  Google Scholar 

  82. Tononi, G., Boly, M., Massimini, M., Koch, C.: Integrated information theory: from consciousness to its physical substrate. Nat. Rev. Neurosci. 17, 450 (2016). https://doi.org/10.1038/nrn.2016.44

    Article  Google Scholar 

  83. Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. ar**v:1806.01261 [cs, stat] (2018)

  84. Gothoskar, N., Guntupalli, J.S., Rikhye, R.V., Lázaro-Gredilla, M., George, D.: Different clones for different contexts: hippocampal cognitive maps as higher-order graphs of a cloned HMM. bioRxiv. 745950 (2019) https://doi.org/10.1101/745950

  85. Peer, M., Brunec, I.K., Newcombe, N.S., Epstein, R.A.: Structuring knowledge with cognitive maps and cognitive graphs. Trends Cogn. Sci. 25, 37–54 (2021). https://doi.org/10.1016/j.tics.2020.10.004

    Article  Google Scholar 

  86. Dehaene, S.: Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts. Viking, New York (2014)

    Google Scholar 

  87. Tononi, G., Koch, C.: Consciousness: here, there and everywhere? Philos. Trans. R. Soc. B: Biol. Sci. 370, 20140167 (2015). https://doi.org/10.1098/rstb.2014.0167

  88. Ortiz, J., Pupilli, M., Leutenegger, S., Davison, A.J.: Bundle adjustment on a graph processor. ar**v:2003.03134 [cs] (2020)

  89. Kahneman, D.: Thinking, Fast and Slow. Farrar, Straus and Giroux (2011)

    Google Scholar 

  90. Bengio, Y.: The consciousness prior. ar**v:1709.08568 [cs, stat] (2017)

  91. Lange, S., Riedmiller, M.: Deep auto-encoder neural networks in reinforcement learning. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2010). https://doi.org/10.1109/IJCNN.2010.5596468

  92. Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. ar**v:1605.08104 [cs, q-bio] (2016)

  93. Wu, Y., Wayne, G., Graves, A., Lillicrap, T.: The Kanerva machine: a generative distributed memory. ar**v:1804.01756 [cs, stat] (2018)

  94. Jiang, Y., Kim, H., Asnani, H., Kannan, S., Oh, S., Viswanath, P.: Turbo autoencoder: deep learning based channel codes for point-to-point communication channels. ar**v:1911.03038 [cs, eess, math] (2019)

  95. Kanai, R., Chang, A., Yu, Y., Magrans de Abril, I., Biehl, M., Guttenberg, N.: Information generation as a functional basis of consciousness. Neurosci. Conscious. 2019 (2019). https://doi.org/10.1093/nc/niz016

  96. Lillicrap, T.P., Santoro, A., Marris, L., Akerman, C.J., Hinton, G.: Backpropagation and the brain. Nat. Rev. Neurosci. 1–12 (2020). https://doi.org/10.1038/s41583-020-0277-3

  97. Dayan, P., Hinton, G.E., Neal, R.M., Zemel, R.S.: The Helmholtz machine. Neural Comput. 7, 889–904 (1995)

    Article  Google Scholar 

  98. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. ar**v:1312.6114 [cs, stat] (2014)

  99. Candadai, M., Izquierdo, E.J.: Sources of predictive information in dynamical neural networks. Sci. Rep. 10, 16901 (2020). https://doi.org/10.1038/s41598-020-73380-x

    Article  Google Scholar 

  100. Lu, Z., Bassett, D.S.: Invertible generalized synchronization: a putative mechanism for implicit learning in neural systems. Chaos 30, 063133 (2020). https://doi.org/10.1063/5.0004344

    Article  MathSciNet  MATH  Google Scholar 

  101. Rumelhart, D.E., McClelland, J.L.: Information processing in dynamical systems: foundations of harmony theory. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations, pp. 194–281. MIT Press (1987)

    Google Scholar 

  102. Kachman, T., Owen, J.A., England, J.L.: Self-organized resonance during search of a diverse chemical space. Phys. Rev. Lett. 119, 038001 (2017). https://doi.org/10.1103/PhysRevLett.119.038001

    Article  Google Scholar 

  103. Friston, K.J.: A free energy principle for a particular physics. ar**v:1906.10184 [q-bio] (2019)

  104. Ali, A., Ahmad, N., de Groot, E., van Gerven, M.A.J., Kietzmann, T.C.: Predictive coding is a consequence of energy efficiency in recurrent neural networks. bioRxiv. 2021.02.16.430904 (2021). https://doi.org/10.1101/2021.02.16.430904

  105. Bejan, A., Lorente, S.: The constructal law of design and evolution in nature. Philos. Trans. R. Soc. Lond. B Biol. Sci. 365, 1335–1347 (2010). https://doi.org/10.1098/rstb.2009.0302

    Article  Google Scholar 

  106. McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)

    Article  MathSciNet  MATH  Google Scholar 

  107. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  108. Ahmad, S., Scheinkman, L.: How can we be so dense? The benefits of using highly sparse representations. ar**v preprint ar**v:1903.11257 (2019)

  109. Mumford, D.: On the computational architecture of the neocortex. Biol. Cybern. 65, 135–145 (1991). https://doi.org/10.1007/BF00202389

    Article  Google Scholar 

  110. Rao, R.P., Ballard, D.H.: Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nat. Neurosci. 2, 79–87 (1999). https://doi.org/10.1038/4580

    Article  Google Scholar 

  111. Bastos, A.M., Usrey, W.M., Adams, R.A., Mangun, G.R., Fries, P., Friston, K.J.: Canonical microcircuits for predictive coding. Neuron 76, 695–711 (2012). https://doi.org/10.1016/j.neuron.2012.10.038

    Article  Google Scholar 

  112. Grossberg, S.: Towards solving the hard problem of consciousness: the varieties of brain resonances and the conscious experiences that they support. Neural Netw. 87, 38–95 (2017). https://doi.org/10.1016/j.neunet.2016.11.003

    Article  Google Scholar 

  113. Heeger, D.J.: Theory of cortical function. Proc. Natl. Acad. Sci. U.S.A. 114, 1773–1782 (2017). https://doi.org/10.1073/pnas.1619788114

    Article  MathSciNet  MATH  Google Scholar 

  114. George, D., Lázaro-Gredilla, M., Lehrach, W., Dedieu, A., Zhou, G.: A detailed mathematical theory of thalamic and cortical microcircuits based on inference in a generative vision model. bioRxiv. 2020.09.09.290601 (2020). https://doi.org/10.1101/2020.09.09.290601

  115. Friston, K.J., Rosch, R., Parr, T., Price, C., Bowman, H.: Deep temporal models and active inference. Neurosci. Biobehav. Rev. 77, 388–402 (2017). https://doi.org/10.1016/j.neubiorev.2017.04.009

    Article  Google Scholar 

  116. Pearl, J., Mackenzie, D.: The Book of Why: The New Science of Cause and Effect. Basic Books (2018)

    Google Scholar 

  117. Csáji, B.C.: Approximation with artificial neural networks. Fac. Sci. Etvs Lornd Univ. Hungary. 24, 7 (2001)

    Google Scholar 

  118. Malach, E., Shalev-Shwartz, S.: Is deeper better only when shallow is good? ar**v:1903.03488 [cs, stat] (2019)

  119. Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. ar**v:1505.00387 [cs] (2015)

  120. Lin, H.W., Tegmark, M., Rolnick, D.: Why does deep and cheap learning work so well? J. Stat. Phys. 168(6), 1223–1247 (2017). https://doi.org/10.1007/s10955-017-1836-5

    Article  MathSciNet  MATH  Google Scholar 

  121. Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys. D 404, 132306 (2020). https://doi.org/10.1016/j.physd.2019.132306

    Article  MathSciNet  MATH  Google Scholar 

  122. Schmidhuber, J.: On learning how to learn learning strategies (1994)

    Google Scholar 

  123. Wang, J.X., et al.: Prefrontal cortex as a meta-reinforcement learning system. Nat. Neurosci. 21, 860 (2018). https://doi.org/10.1038/s41593-018-0147-8

    Article  Google Scholar 

  124. Watts, D.J., Strogatz, S.H.: Collective dynamics of ‘small-world’ networks. Nature 393, 440 (1998). https://doi.org/10.1038/30918

    Article  MATH  Google Scholar 

  125. Jarman, N., Steur, E., Trengove, C., Tyukin, I.Y., van Leeuwen, C.: Self-organisation of small-world networks by adaptive rewiring in response to graph diffusion. Sci. Rep. 7, 13158 (2017). https://doi.org/10.1038/s41598-017-12589-9

    Article  Google Scholar 

  126. Rentzeperis, I., Laquitaine, S., van Leeuwen, C.: Adaptive rewiring of random neural networks generates convergent-divergent units. ar**v:2104.01418 [q-bio] (2021)

  127. Massobrio, P., Pasquale, V., Martinoia, S.: Self-organized criticality in cortical assemblies occurs in concurrent scale-free and small-world networks. Sci. Rep. 5, 10578 (2015). https://doi.org/10.1038/srep10578

    Article  Google Scholar 

  128. Gal, E., et al.: Rich cell-type-specific network topology in neocortical microcircuitry. Nat. Neurosci. 20, 1004–1013 (2017). https://doi.org/10.1038/nn.4576

    Article  Google Scholar 

  129. Takagi, K.: Information-based principle induces small-world topology and self-organized criticality in a large scale brain network. Front. Comput. Neurosci. 12 (2018). https://doi.org/10.3389/fncom.2018.00065

  130. Goekoop, R., de Kleijn, R.: How higher goals are constructed and collapse under stress: a hierarchical Bayesian control systems perspective. Neurosci. Biobehav. Rev. 123, 257–285 (2021). https://doi.org/10.1016/j.neubiorev.2020.12.021

    Article  Google Scholar 

  131. Sporns, O.: Network attributes for segregation and integration in the human brain. Curr. Opin. Neurobiol. 23, 162–171 (2013). https://doi.org/10.1016/j.conb.2012.11.015

    Article  Google Scholar 

  132. Cohen, J.R., D’Esposito, M.: The segregation and integration of distinct brain networks and their relationship to cognition. J. Neurosci. 36, 12083–12094 (2016). https://doi.org/10.1523/JNEUROSCI.2965-15.2016

    Article  Google Scholar 

  133. Mohr, H., et al.: Integration and segregation of large-scale brain networks during short-term task automatization. Nat Commun. 7, 13217 (2016). https://doi.org/10.1038/ncomms13217

    Article  Google Scholar 

  134. Badcock, P.B., Friston, K.J., Ramstead, M.J.D.: The hierarchically mechanistic mind: a free-energy formulation of the human psyche. Phys. Life Rev. (2019). https://doi.org/10.1016/j.plrev.2018.10.002

    Article  Google Scholar 

  135. Bak, P., Sneppen, K.: Punctuated equilibrium and criticality in a simple model of evolution. Phys. Rev. Lett. 71, 4083–4086 (1993). https://doi.org/10.1103/PhysRevLett.71.4083

    Article  Google Scholar 

  136. Edelman, G., Gally, J.A., Baars, B.J.: Biology of consciousness. Front Psychol. 2, 4 (2011). https://doi.org/10.3389/fpsyg.2011.00004

    Article  Google Scholar 

  137. Paperin, G., Green, D.G., Sadedin, S.: Dual-phase evolution in complex adaptive systems. J. R. Soc. Interface 8, 609–629 (2011). https://doi.org/10.1098/rsif.2010.0719

    Article  Google Scholar 

  138. Safron, A., Klimaj, V., Hipólito, I.: On the importance of being flexible: dynamic brain networks and their potential functional significances (2021). https://psyarxiv.com/x734w/, https://doi.org/10.31234/osf.io/x734w

  139. Safron, A.: Integrated world modeling theory (IWMT) expanded: implications for theories of consciousness and artificial intelligence (2021). https://psyarxiv.com/rm5b2/, https://doi.org/10.31234/osf.io/rm5b2

  140. Smith, R.: Do brains have an arrow of time? Philos. Sci. 81, 265–275 (2014). https://doi.org/10.1086/675644

    Article  Google Scholar 

  141. Wolfram, S.: A New Kind of Science. Wolfram Media (2002)

    Google Scholar 

  142. Friston, K.J., Wiese, W., Hobson, J.A.: Sentience and the origins of consciousness: from cartesian duality to Markovian monism. Entropy 22, 516 (2020). https://doi.org/10.3390/e22050516

    Article  MathSciNet  Google Scholar 

  143. Doerig, A., Schurger, A., Hess, K., Herzog, M.H.: The unfolding argument: why IIT and other causal structure theories cannot explain consciousness. Conscious. Cogn. 72, 49–59 (2019). https://doi.org/10.1016/j.concog.2019.04.002

    Article  Google Scholar 

  144. Marshall, W., Kim, H., Walker, S.I., Tononi, G., Albantakis, L.: How causal analysis can reveal autonomy in models of biological systems. Phil. Trans. R. Soc. A. 375, 20160358 (2017). https://doi.org/10.1098/rsta.2016.0358

    Article  Google Scholar 

  145. Joslyn, C.: Levels of control and closure in complex semiotic systems. Ann. N. Y. Acad. Sci. 901, 67–74 (2000)

    Google Scholar 

  146. Chang, A.Y.C., Biehl, M., Yu, Y., Kanai, R.: Information closure theory of consciousness. ar**v:1909.13045 [q-bio] (2019)

  147. Singer, W.: Consciousness and the binding problem. Ann. N. Y. Acad. Sci. 929, 123–146 (2001)

    Article  Google Scholar 

  148. Baars, B.J., Franklin, S., Ramsoy, T.Z.: Global workspace dynamics: cortical “binding and propagation” enables conscious contents. Front Psychol. 4 (2013). https://doi.org/10.3389/fpsyg.2013.00200

  149. Atasoy, S., Donnelly, I., Pearson, J.: Human brain networks function in connectome-specific harmonic waves. Nat. Commun. 7, 10340 (2016). https://doi.org/10.1038/ncomms10340

    Article  Google Scholar 

  150. Wu, L., Zhang, Y.: A new topological approach to the L∞-uniqueness of operators and the L1-uniqueness of Fokker-Planck equations. J. Funct. Anal. 241, 557–610 (2006). https://doi.org/10.1016/j.jfa.2006.04.020

    Article  MathSciNet  MATH  Google Scholar 

  151. Carroll, S.: The Big Picture: On the Origins of Life, Meaning, and the Universe Itself. Penguin (2016)

    Google Scholar 

  152. Hoel, E.P., Albantakis, L., Marshall, W., Tononi, G.: Can the macro beat the micro? Integrated information across spatiotemporal scales. Neurosci. Conscious. 2016 (2016). https://doi.org/10.1093/nc/niw012

  153. Albantakis, L., Marshall, W., Hoel, E., Tononi, G.: What caused what? A quantitative account of actual causation using dynamical causal networks. ar**v:1708.06716 [cs, math, stat] (2017)

  154. Hoel, E.P.: When the map is better than the territory. Entropy 19, 188 (2017). https://doi.org/10.3390/e19050188

    Article  Google Scholar 

  155. Rocha, L.M.: Syntactic autonomy. Why there is no autonomy without symbols and how self-organizing systems might evolve them. Ann. N. Y. Acad. Sci. 901, 207–223 (2000). https://doi.org/10.1111/j.1749-6632.2000.tb06280.x

  156. Rudrauf, D., Lutz, A., Cosmelli, D., Lachaux, J.-P., Le Van Quyen, M.: From autopoiesis to neurophenomenology: Francisco Varela’s exploration of the biophysics of being. Biol. Res. 36, 27–65 (2003)

    Article  Google Scholar 

  157. Everhardt, A.S., et al.: Periodicity-doubling cascades: direct observation in ferroelastic materials. Phys. Rev. Lett. 123, 087603 (2019). https://doi.org/10.1103/PhysRevLett.123.087603

    Article  Google Scholar 

  158. Chen, T., et al.: Quantum Zeno effects across a parity-time symmetry breaking transition in atomic momentum space (2020)

    Google Scholar 

  159. Fruchart, M., Hanai, R., Littlewood, P.B., Vitelli, V.: Non-reciprocal phase transitions. Nature 592, 363–369 (2021). https://doi.org/10.1038/s41586-021-03375-9

    Article  Google Scholar 

  160. Hofstadter, D.R.: Gödel, Escher, Bach: An Eternal Golden Braid. Basic Books (1979)

    Google Scholar 

  161. Hofstadter, D.R.: I Am a Strange Loop. Basic Books (2007)

    Google Scholar 

  162. Lloyd, S.: A Turing test for free will. Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. 370, 3597–3610 (2012). https://doi.org/10.1098/rsta.2011.0331

    Article  MATH  Google Scholar 

  163. Parr, T., Markovic, D., Kiebel, S.J., Friston, K.J.: Neuronal message passing using mean-field, Bethe, and marginal approximations. Sci. Rep. 9 (2019). https://doi.org/10.1038/s41598-018-38246-3

  164. Madl, T., Baars, B.J., Franklin, S.: The timing of the cognitive cycle. PLoS One 6, e14803 (2011)

    Article  Google Scholar 

  165. Maguire, P., Maguire, R.: Consciousness is data compression. Undefined (2010)

    Google Scholar 

  166. Tegmark, M.: Improved measures of integrated information. PLoS Comput Biol. 12 (2016). https://doi.org/10.1371/journal.pcbi.1005123

  167. Maguire, P., Moser, P., Maguire, R.: Understanding consciousness as data compression. J. Cogn. Sci. 17, 63–94 (2016)

    Article  Google Scholar 

  168. Metzinger, T.: The Ego Tunnel: The Science of the Mind and the Myth of the Self. Basic Books, New York (2009)

    Google Scholar 

  169. Limanowski, J., Friston, K.J.: ‘Seeing the dark’: grounding phenomenal transparency and opacity in precision estimation for active inference. Front. Psychol. 9 (2018). https://doi.org/10.3389/fpsyg.2018.00643

  170. Hoffman, D.D., Prakash, C.: Objects of consciousness. Front. Psychol. 5 (2014). https://doi.org/10.3389/fpsyg.2014.00577

  171. Kirchhoff, M., Parr, T., Palacios, E., Friston, K.J., Kiverstein, J.: The Markov blankets of life: autonomy, active inference and the free energy principle. J. R. Soc. Interface 15 (2018). https://doi.org/10.1098/rsif.2017.0792

  172. Dennett, D.: Consciousness Explained. Back Bay Books (1992)

    Google Scholar 

  173. Haun, A., Tononi, G.: Why does space feel the way it does? Towards a principled account of spatial experience. Entropy 21, 1160 (2019). https://doi.org/10.3390/e21121160

    Article  MathSciNet  Google Scholar 

  174. Sutterer, D.W., Polyn, S.M., Woodman, G.F.: α-band activity tracks a two-dimensional spotlight of attention during spatial working memory maintenance. J. Neurophysiol. 125, 957–971 (2021). https://doi.org/10.1152/jn.00582.2020

    Article  Google Scholar 

Download references

Acknowledgments

In addition to collaborators who have taught me countless lessons over many years, I would like to thank Jürgen Schmidhuber and Karl Friston for their generous feedback on previous versions of these discussions. Any errors (either technical or stylistic) are entirely my own.

Author information

Authors and Affiliations

  1. Center for Psychedelic & Consciousness Research, Department of Psychiatry & Behavioral Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Adam Safron

  2. Cognitive Science Program, Indiana University, Bloomington, IN, USA

    Adam Safron

  3. Institute for Advanced Consciousness Studies, Santa Monica, CA, USA

    Adam Safron

Authors
  1. Adam Safron
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Adam Safron .

Editor information

Editors and Affiliations

  1. University of Sussex, Brighton, UK

    Christopher L. Buckley

  2. University of Chieti-Pescara, Pescara, Italy

    Daniela Cialfi

  3. Donders Institute for Brain, Cognition and Behaviour, Nijmegen, The Netherlands

    Pablo Lanillos

  4. Wellcome Centre for Human Neuroimaging, London, UK

    Maxwell Ramstead

  5. Wellcome Centre for Human Neuroimaging, London, UK

    Noor Sajid

  6. Kyoto University, Kyoto, Japan

    Hideaki Shimazaki

  7. Ghent University, Ghent, Belgium

    Tim Verbelen

A Appendix

A Appendix

1.1 A.1 Recurrent Networks, Universal Computation, and Generalized Predictive Coding

In describing brain function in terms of generative modeling, IWMT attempts to characterize different aspects of nervous systems in terms of principles from machine learning. Autoencoders are identified as a particularly promising framework for understanding cortical generative models due to their architectural structures reflecting core principles of FEP-AI (and AIXI). By training systems to reconstruct data while filtering (or compressing) information through dimensionality-reducing bottlenecks, this process induces the discovery of both accurate and parsimonious models of data in the service of the adaptive control of behavior [91]. IWMT’s description of cortical hierarchies as consisting of “folded” autoencoders was proposed to provide a bridge between machine learning and predictive-coding models of cortical functioning. Encouraging convergence may be found in that these autoencoder-inspired models were developed without knowledge of similar proposals by others [10], and shared latent spaces structured according to the principles of geometric deep learning (however, subsequent work by Schmidhuber and colleagues has begun to move in this direction [124], so allowing for a synergistic combination of integrating both local and global informational dependencies. Such deep learning systems are even more effective if these skip connections are adaptively configurable [10]—understood as a kind of generalized search/navigation process—including with respect to reverse engineering such functions in attempting to design (and/or grow) intelligent machines [2].

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Safron, A. (2023). AIXI, FEP-AI, and Integrated World Models: Towards a Unified Understanding of Intelligence and Consciousness. In: Buckley, C.L., et al. Active Inference. IWAI 2022. Communications in Computer and Information Science, vol 1721. Springer, Cham. https://doi.org/10.1007/978-3-031-28719-0_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-28719-0_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-28718-3

  • Online ISBN: 978-3-031-28719-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation