Skip to main content

Advertisement

SpringerLink
Log in

The intentional stance as structure learning: a computational perspective on mindreading

  • Original Paper
  • Published:
Biological Cybernetics Aims and scope Submit manuscript

Abstract

Recent theories of mindreading explain the recognition of action, intention, and belief of other agents in terms of generative architectures that model the causal relations between observables (e.g., observed movements) and their hidden causes (e.g., action goals and beliefs). Two kinds of probabilistic generative schemes have been proposed in cognitive science and robotics that link to a “theory theory” and “simulation theory” of mindreading, respectively. The former compares perceived actions to optimal plans derived from rationality principles and conceptual theories of others’ minds. The latter reuses one’s own internal (inverse and forward) models for action execution to perform a look-ahead mental simulation of perceived actions. Both theories, however, leave one question unanswered: how are the generative models – including task structure and parameters – learned in the first place? We start from Dennett’s “intentional stance” proposal and characterize it within generative theories of action and intention recognition. We propose that humans use an intentional stance as a learning bias that sidesteps the (hard) structure learning problem and bootstraps the acquisition of generative models for others’ actions. The intentional stance corresponds to a candidate structure in the generative scheme, which encodes a simplified belief-desire folk psychology and a hierarchical intention-to-action organization of behavior. This simple structure can be used as a proxy for the “true” generative structure of others’ actions and intentions and is continuously grown and refined – via state and parameter learning – during interactions. In turn – as our computational simulations show – this can help solve mindreading problems and bootstrap the acquisition of useful causal models of both one’s own and others’ goal-directed actions.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. These are the binary variables used to enforce transition constraints between the two levels in the hierarchy, namely the blocking constraint (i.e., the high-level state cannot change before the low-level sequence has terminated, that is, \(E^{\text {L}}_t=0 \Rightarrow X^{\text {H}}_t=X^{\text {H}}_{t-1}\)) and the termination constraint (i.e., the high-level state cannot terminate before the low-level sequence has terminated, that is, \(E^{\text {L}}_t=0 \Rightarrow E^{\text {H}}_t=0\)).

  2. This idea is consistent with neural evidence for the way humans represent actions, which ranges from simple kinematic acts to more complex assemblies of goal-directed behaviors [48].

  3. As an example, in a monodimensional feature space representing the velocity, the basic behaviors (nodes) could be as follows: still (null value), walking (medium value), running (high value).

  4. Indeed, a comparison of ITM against well-kwown self-organizing maps [58] and growing neural gas [39] is performed in [54] and it is shown that ITM outperfoms the others even in high-dimensional feature spaces.

References

  1. Aarts H, Gollwitzer P, Hassin R (2004) Goal contagion: perceiving is for pursuing. J Pers Soc Psychol 87:23–37

    Article  PubMed  Google Scholar 

  2. Acuna DE, Schrater P (2010) Structure learning in human sequential decision-making. PLoS Comput Biol 6(12):e1001003. doi:10.1371/journal.pcbi.1001003

    Article  PubMed Central  PubMed  Google Scholar 

  3. Arulampalam MS, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174–188

    Article  Google Scholar 

  4. Baker C, Tenenbaum J, Saxe R (2006) Bayesian models of human action understanding. In: Weiss Y, Schölkopf B, Platt J (eds) Advances in neural information processing systems 18. MIT Press, Cambridge, pp 99–106

    Google Scholar 

  5. Baker CL, Saxe R, Tenenbaum JB (2009) Action understanding as inverse planning. Cognition 113(3):329–349. doi:10.1016/j.cognition.2009.07.005

    Article  PubMed  Google Scholar 

  6. Baker CL, Saxe RR, Tenenbaum JB (2011) Bayesian theory of mind: modeling joint belief-desire attribution. In: Proceedings of the thirty-second annual conference of the cognitive science society

  7. Bauer E, Koller D, Singer Y (1997) Update rules for parameter estimation in Bayesian networks. In: Proceedings of the thirteenth conference on uncertainty in artificial intelligence. Morgan Kaufmann Publishers Inc, pp 3–13

  8. Becchio C, Manera V, Sartori L, Cavallo A, Castiello U (2012) Grasping intentions: from thought experiments to empirical evidence. Front Hum Neurosci 6:117. doi:10.3389/fnhum.2012.00117

    Article  PubMed Central  PubMed  Google Scholar 

  9. Bishop CM (2006) Pattern recognition and machine learning. Springer, New York

    Google Scholar 

  10. Blakemore SJ, Frith C (2005) The role of motor contagion in the prediction of action. Neuropsychologia 43(2):260–267. doi:10.1016/j.neuropsychologia.2004.11.012

    Article  PubMed  Google Scholar 

  11. Braun DA, Mehring C, Wolpert DM (2010) Structure learning in action. Behav Brain Res 206(2):157–165. doi:10.1016/j.bbr.2009.08.031

    Article  PubMed Central  PubMed  Google Scholar 

  12. Carroll CD, Kemp C (2013) Hypothesis space checking in intuitive reasoning. In: Proceedings of the 35th annual conference of the cognitive science society. Cognitive science society

  13. Chella A, Dindo H, Infantino I (2007) Imitation learning and anchoring through conceptual spaces. Appl Artif Intell 21(4–5):343–359. doi:10.1080/08839510701252619

    Article  Google Scholar 

  14. Chersi F (2011) Neural mechanisms and models underlying joint action. Exp Brain Res 211(3–4):643–653. doi:10.1007/s00221-011-2690-3

    Article  PubMed  Google Scholar 

  15. Chersi F (2012) Learning through imitation: a biological approach to robotics. IEEE Trans Auton Ment Dev 4(3):204–214. doi:10.1109/TAMD.2012.2200250

    Article  Google Scholar 

  16. Chickering DM, Geiger D, Heckerman D et al (1994) Learning Bayesian networks is NP-hard. Tech. rep, Citeseer

  17. Cho HC, Fadali SM (2006) Online estimation of dynamic Bayesian network parameter. In: IEEE International joint conference on neural networks, 2006, IJCNN’06, pp 3363–3370

  18. Cohen I, Bronstein A, Cozman FG (2001) Adaptive online learning of Bayesian network parameters. University of Sao Paulo, Brasil

    Google Scholar 

  19. Csibra G (2007) Action mirroring and action understanding: an alternative account. In: Haggard P, Rosetti Y, Kawato M (eds) Sensorimotor foundations of higher cognition: attention and performance XXII. Oxford University Press, Oxford

    Google Scholar 

  20. Csibra G, Gergely G (2007) Obsessed with goals: functions and mechanisms of teleological interpretation of actions in humans. Acta Psychol 124:60–78

    Article  Google Scholar 

  21. Csibra G, Gergely G (2009) Natural pedagogy. Trends Cogn Sci 13(4):148–153. doi:10.1016/j.tics.2009.01.005

    Article  PubMed  Google Scholar 

  22. Cuijpers RH, van Schie HT, Koppen M, Erlhagen W, Bekkering H (2006) Goals and means in action observation: a computational approach. Neural Netw 19(3):311–322. doi:10.1016/j.neunet.2006.02.004

    Article  PubMed  Google Scholar 

  23. Dearden A, Demiris Y (2005) Learning forward models for robotics. In: Proceedings of IJCAI-2005. Edinburgh, pp 1440–1445

  24. Demiris J, Hayes G (2002) Imitation as a dual-route process featuring predictive and learning components: a biologically plausible computational model. Imitation in animals and artifacts. MIT Press, Cambridge, pp 327–361

    Google Scholar 

  25. Demiris Y (2007) Prediction of intent in robotics and multi-agent systems. Cogn Process 8(3):151–158

    Article  PubMed  Google Scholar 

  26. Demiris Y, Khadhouri B (2005) Hierarchical attentive multiple models for execution and recognition (Hammer). Rob Auton Syst J 54:361–369

    Article  Google Scholar 

  27. Dennett D (1987) The intentional stance. MIT Press, Cambridge

    Google Scholar 

  28. Dindo H, Schillaci G (2010) An adaptive probabilistic graphical model for representing skills in pbd settings. In: Proceedings of the 5th ACM/IEEE international conference on human-robot interaction, pp 89–90

  29. Dindo H, Schillaci G (2010) An adaptive probabilistic approach to goal-level imitation learning. In: Proceedings of the 2010 IEEE/RSJ international conference on intelligent robots and systems (IROS), pp 4452–4457. doi:10.1109/IROS.2010.5654440

  30. Dindo H, Zambuto D, Pezzulo G (2011) Motor simulation via coupled internal models using sequential Monte Carlo. Proceedings of IJCAI 2011:2113–2119

    Google Scholar 

  31. Doucet A, De Freitas N, Gordon N et al (2001) Sequential Monte Carlo methods in practice, vol 1. Springer, New York

    Book  Google Scholar 

  32. Fadiga L, Fogassi L, Pavesi G, Rizzolatti G (1995) Motor facilitation during action observation: a magnetic stimulation study. J Neurophysiol 73:2608–2611

    CAS  PubMed  Google Scholar 

  33. Friston K (2005) A theory of cortical responses. Philos Trans R Soc Lond B Biol Sci 360(1456):815–836. doi:10.1098/rstb.2005.1622

    Article  PubMed Central  PubMed  Google Scholar 

  34. Friston K, Mattout J, Kilner J (2011) Action understanding and active inference. Biol Cybern 104(1–2):137–160. doi:10.1007/s00422-011-0424-z

    Article  PubMed Central  PubMed  Google Scholar 

  35. Friston KJ, Daunizeau J, Kilner J, Kiebel SJ (2010) Action and behavior: a free-energy formulation. Biol Cybern 102(3):227–260. doi:10.1007/s00422-010-0364-z

    Article  PubMed  Google Scholar 

  36. Frith CD, Frith U (2006) How we predict what other people are going to do. Brain Res 1079(1):36–46. doi:10.1016/j.brainres.2005.12.126. http://www.sciencedirect.com/science/article/B6SYR-4JCCJXS-3/2/ec6adb1fa305f3d6791ac45f451cf63d

  37. Frith CD, Frith U (2008) Implicit and explicit processes in social cognition. Neuron 60(3):503–510. doi:10.1016/j.neuron.2008.10.032

    Article  CAS  PubMed  Google Scholar 

  38. Frith U, Frith C (2010) The social brain: allowing humans to boldly go where no other species has been. Philos Trans R Soc Lond B Biol Sci 365(1537):165–176. doi:10.1098/rstb.2009.0160

    Article  PubMed Central  PubMed  Google Scholar 

  39. Fritzke B et al (1995) A growing neural gas network learns topologies. Adv Neural Inf Process Syst 7:625–632

    Google Scholar 

  40. Gallagher HL, Jack AI, Roepstorff A, Frith CD (2002) Imaging the intentional stance in a competitive game. Neuroimage 16(3 Pt 1):814–821

    Article  PubMed  Google Scholar 

  41. Gallese V, Fadiga L, Fogassi L, Rizzolatti G (1996) Action recognition in the premotor cortex. Brain 119:593–609

    Article  PubMed  Google Scholar 

  42. Garrod S, Pickering MJ (2009) Joint action, interactive alignment, and dialog. Top Cogn Sci 1(2):292–304. doi:10.1111/j.1756-8765.2009.01020.x

    Article  PubMed  Google Scholar 

  43. Gergely G, Csibra G (2003) Teleological reasoning in infancy: the naive theory of rational action. Trends Cogn Sci 7:287–292

    Article  PubMed  Google Scholar 

  44. Gershman SJ, Niv Y (2010) Learning latent structure: carving nature at its joints. Curr Opin Neurobiol 20(2):251–256. doi:10.1016/j.conb.2010.02.008

    Article  PubMed Central  CAS  PubMed  Google Scholar 

  45. Gopnik A, Glymour C, Sobel DM, Schulz LE, Kushnir T, Danks D (2004) A theory of causal learning in children: causal maps and Bayes nets. Psychol Rev 111(1):3–32. doi:10.1037/0033-295X.111.1.3

    Article  PubMed  Google Scholar 

  46. Gopnik A, Meltzoff A (1997) Words, thoughts and theories. MIT Press, Cambridge

    Google Scholar 

  47. Grush R (2004) The emulation theory of representation: motor control, imagery, and perception. Behav Brain Sci 27(3):377–396

    PubMed  Google Scholar 

  48. Hamilton AFdC, Grafton ST (2007) The motor hierarchy: from kinematics to goals and intentions. In: Haggard P, Rossetti Y, Kawato M (eds) Sensorimotor foundations of higher cognition. Oxford University Press, Oxford

    Google Scholar 

  49. Heckerman D (1998) A tutorial on learning with Bayesian networks. Springer, New York

    Book  Google Scholar 

  50. Heil L, van Pelt S, Kwisthout J, van Rooij I, Bekkering H (2014) Higher-level processes in the formation and application of associations during action understanding. Behav Brain Sci 37(02):202–203

    Article  PubMed  Google Scholar 

  51. Hommel B, Musseler J, Aschersleben G, Prinz W (2001) The theory of event coding (tec): a framework for perception and action planning. Behav Brain Sci 24(5):849–878

    Article  CAS  PubMed  Google Scholar 

  52. Jeannerod M (2001) Neural simulation of action: a unifying mechanism for motor cognition. NeuroImage 14:S103–S109

    Article  CAS  PubMed  Google Scholar 

  53. Jeannerod M (2006) Motor cognition. Oxford University Press, Oxford

    Book  Google Scholar 

  54. Jockusch J, Ritter H (1999) An instantaneous topological mapping model for correlated stimuli. In: Proceedings of the international joint conference on neural networks, Washington (US), vol 1, pp 529–534

  55. Kiebel SJ, von Kriegstein K, Daunizeau J, Friston KJ (2009) Recognizing sequences of sequences. PLoS Comput Biol 5(8):e1000464. doi:10.1371/journal.pcbi.1000464

    Article  PubMed Central  PubMed  Google Scholar 

  56. Kilner JM (2011) More than one pathway to action understanding. Trends Cogn Sci 15(8):352–357. doi:10.1016/j.tics.2011.06.005

    Article  PubMed Central  PubMed  Google Scholar 

  57. Kilner JM, Friston KJ, Frith CD (2007) Predictive coding: an account of the mirror neuron system. Cogn Process 8(3):159–166

    Article  PubMed Central  PubMed  Google Scholar 

  58. Kohonen T (1998) The self-organizing map. Neurocomputing 21(1):1–6

    Article  Google Scholar 

  59. Koller D, Friedman N (2009) Probabilistic graphical models: principles and techniques. MIT Press, Cambridge

    Google Scholar 

  60. Levinson SC (2006) On the human “interaction engine”. In: Enfield NJ, Levinson SC (eds) Roots of human sociality: culture, cognition and interaction. Berg, Oxford, pp 39–69

    Google Scholar 

  61. Liang P, Klein D (2009) Online em for unsupervised models. In: Proceedings of human language technologies: the 2009 annual conference of the North American chapter of the association for computational linguistics, pp 611–619. Association for computational linguistics

  62. Meltzoff AN (2007) ’like me’: a foundation for social cognition. Dev Sci 10(1):126–134. doi:10.1111/j.1467-7687.2007.00574.x

    Article  PubMed Central  PubMed  Google Scholar 

  63. Murphy KP (2002) Dynamic Bayesian networks: representation, inference and learning. Ph.D. thesis, UC Berkeley, Computer Science Division. http://www.worldcat.org/oclc/52827959

  64. Murphy KP (2012) Machine learning: a probabilistic perspective. MIT Press, Cambridge

    Google Scholar 

  65. Neal RM, Hinton GE (1998) A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Jordan MI (ed) Learning in graphical models. Kluwer Academic Publishers, Norwell, pp 355–368

  66. Ognibene D, Wu Y, Lee K, Demiris Y (2013) Hierarchies for embodied action perception. In: Computational and robotic models of the hierarchical organization of behavior. Springer, pp 81–98

  67. Pacherie E (2008) The phenomenology of action: a conceptual framework. Cognition 107:179–217

    Article  PubMed  Google Scholar 

  68. Pearl J (2000) Causality: models, reasoning, and inference. Cambridge University Press, Cambridge

    Google Scholar 

  69. Pezzulo G (2008) Coordinating with the future: the anticipatory nature of representation. Minds Mach 18(2):179–225. doi:10.1007/s11023-008-9095-5

    Article  Google Scholar 

  70. Pezzulo G (2011) Grounding procedural and declarative knowledge in sensorimotor anticipation. Mind Lang 26(1):78–114

    Article  Google Scholar 

  71. Pezzulo G (2012) The interaction engine: a common pragmatic competence across linguistic and non-linguistic interactions. IEEE Trans Auton Ment Dev 4(2):105–123

    Article  Google Scholar 

  72. Pezzulo G (2013) Studying mirror mechanisms within generative and predictive architectures for joint action. Cortex 49:2968–2969

    Article  PubMed  Google Scholar 

  73. Pezzulo G, Candidi M, Dindo H, Barca L (2013) Action simulation in the human brain: twelve questions. New Ideas Psychol 31(3):270–290

    Article  Google Scholar 

  74. Pezzulo G, Dindo H (2011) What should i do next? Using shared representations to solve interaction problems. Exp Brain Res 211(3):613–630

    Article  PubMed  Google Scholar 

  75. Pezzulo G, Donnarumma F, Dindo H (2013) Human sensorimotor communication: a theory of signaling in online social interactions. PLoS One 8(11):e79876. doi:10.1371/journal.pone.0079876

    Article  PubMed Central  PubMed  Google Scholar 

  76. Pezzulo G, van der Meer MA, Lansink CS, Pennartz CM (2014) Internally generated sequences in learning and executing goal-directed behavior. Trends Cogn Sci 18(12):647–657

    Article  PubMed  Google Scholar 

  77. Pickering MJ, Garrod S (2007) Do people use language production to make predictions during comprehension? Trends Cogn Sci 11(3):105–110

    Article  PubMed  Google Scholar 

  78. Ramirez M, Geffner H (2010) Probabilistic plan recognition using off-the-shelf classical planners. In: Proceedings of AAAI-10. Atlanta, USA

  79. Ramírez M, Geffner H (2011) Goal recognition over pomdps: inferring the intention of a pomdp agent. In: IJCAI, pp 2009–2014

  80. Schaal S (1999) Is imitation learning the route to humanoid robots? Trends Cogn Sci 3:233–242

    Article  PubMed  Google Scholar 

  81. Sebanz N, Bekkering H, Knoblich G (2006) Joint action: bodies and minds moving together. Trends Cogn Sci 10(2):70–76. doi:10.1016/j.tics.2005.12.009

    Article  PubMed  Google Scholar 

  82. Shadmehr R, Mussa-Ivaldi S (2012) Biological learning and control: how the brain builds representations, predicts events, and makes decisions. MIT Press, Cambridge

    Book  Google Scholar 

  83. Skinner BF (1948) Superstition in the pigeon. J Exp Psychol 38(2):168–172

    Article  CAS  PubMed  Google Scholar 

  84. Teh YW, Jordan MI (2010) Hierarchical Bayesian nonparametric models with applications. Bayesian Nonparametrics. Cambridge University Press, pp 158–207

  85. Tenenbaum JB, Kemp C, Griffiths TL, Goodman ND (2011) How to grow a mind: statistics, structure, and abstraction. Science 331(6022):1279–1285. doi:10.1126/science.1192788

    Article  CAS  PubMed  Google Scholar 

  86. Todorov E, Jordan MI (2002) Optimal feedback control as a theory of motor coordination. Nat Neurosci 5(11):1226–1235. doi:10.1038/nn963

    Article  CAS  PubMed  Google Scholar 

  87. Tomasello M, Carpenter M, Call J, Behne T, Moll H (2005) Understanding and sharing intentions: the origins of cultural cognition. Behav Brain Sci 28(5):675–691. doi:10.1017/S0140525X05000129

    PubMed  Google Scholar 

  88. Ullman T, Tenenbaum J, Baker C, Macindoe O, Evans O, Goodman N et al. (2009) Help or hinder: Bayesian models of social goal inference. In: Proceedings of neural information processing systems

  89. Vasquez D, Fraichard T, Laugier C (2009) Incremental learning of statistical motion patterns with growing hidden markov models. IEEE Trans Intell Trans Syst 10(3):403–416

    Article  Google Scholar 

  90. Wilson M, Knoblich G (2005) The case for motor involvement in perceiving conspecifics. Psychol Bull 131:460–473

    Article  PubMed  Google Scholar 

  91. Wolpert DM, Doya K, Kawato M (2003) A unifying computational framework for motor control and social interaction. Philos Trans R Soc Lond B Biol Sci 358(1431):593–602. doi:10.1098/rstb.2002.1238

    Article  PubMed Central  PubMed  Google Scholar 

Download references

Acknowledgments

The authors would like to thank Guido Schillaci for useful discussions and background materials.

Author information

Authors and Affiliations

  1. RoboticsLab, Polytechnic School (DICGIM), University of Palermo, Viale delle Scienze, Ed. 6, 90128, Palermo, Italy

    Haris Dindo

  2. Institute of Cognitive Sciences and Technologies, National Research Council, Via San Martino della Battaglia 44, 00185, Rome, Italy

    Francesco Donnarumma & Giovanni Pezzulo

  3. Institute of Cognitive Neuroscience, University College London, London, WC1N 3AR, UK

    Fabian Chersi

Authors
  1. Haris Dindo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Francesco Donnarumma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fabian Chersi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Giovanni Pezzulo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Giovanni Pezzulo.

Additional information

The research leading to these results has received funding from the Human Frontier Science Program, Grant RGY0088/2014 to GP, and the European Union Seventh Framework Programme (FP7/2007-2013) under Grant Agreements FP7-270108 (Goal-Leaders) to GP and 604102 (Human Brain Project) to FC.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dindo, H., Donnarumma, F., Chersi, F. et al. The intentional stance as structure learning: a computational perspective on mindreading. Biol Cybern 109, 453–467 (2015). https://doi.org/10.1007/s00422-015-0654-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00422-015-0654-6

Keywords

Search

Navigation