Skip to main content
SpringerLink
Log in
Book cover

Neurodynamics of Cognition and Consciousness pp 185–210Cite as

Shape Recognition Through Dynamic Motor Representations

  • Chapter

  • 1443 Accesses

Part of the Understanding Complex Systems book series (UCS)

Abstract

How can agents, natural or artificial, learn about the external environment based only on its internal state (such as the activation patterns in the brain)? There are two problems involved here: first, forming the internal state based on sensory data to reflect reality, and second, forming thoughts and desires based on these internal states. (Aristotle termed these passive and active intellect, respectively [1].) How are these to be accomplished? Chapters in this book consider mechanisms of the instinct for learning (chapter PERLOVSKY) and reinforcement learning (chapter IFTEKHARUDDIN; chapter WERBOS), which modify the mind’s representation for better fitting sensory data. Our approach (as those in chapters FREEMAN and KOZMA) emphasizes the importance of action in this process. Action plays a key role in recovering sensory stimulus properties that are represented by the internal state. Generating the right kind of action is essential to decoding the internal state. Action that maintains invariance in the internal state are important as it will have the same property as that of the represented sensory stimulus. However, such an approach alone does not address how it can be generalized to learn more complex object concepts. We emphasize that the limitation is due to the reactive nature of the sensorimotor interaction in the agent: lack of long-term memory prevents learning beyond the basic stimulus properties such as orientation of the input. Adding memory can help the learning of complex object concepts, but what kind of memory should be used and why? Themain aim of this chapter is to assess the merit of memory of action sequence linked with a particular spatiotemporal pattern (skill memory), as compared to explicit memory of visual form (visual memory), all within an object recognition domain. Our results indicate that skill memory is (1) better than visual memory in terms of recognition performance, (2) robust to noise and variations, and (3) better suited as a flexible internal representation. These results suggest that the dynamic nature of skill memory, with its involvement in the closure of the agent-environment loop, provides a strong basis for robust and autonomous object concept learning.

Keywords

  • Mean Square Error
  • Internal State
  • Action Sequence
  • Visual Memory
  • Noise Factor

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   129.00
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   169.99
Price excludes VAT (Canada)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD   169.99
Price excludes VAT (Canada)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barnes, J.: Aristotle. In Gregory, R.L., ed.: The Oxford Companion to the Mind. Oxford University Press, Oxford, UK (2004) 45–46

    Google Scholar 

  2. Freeman, W.J.: How Brains Make Up Their Minds. Wiedenfeld and Nicolson Ltd., London, UK (1999) Reprinted by Columbia University Press (2001).

    Google Scholar 

  3. Harnad, S.: The symbol grounding problem. Physica D 42 (1990) 335–346

    CrossRef  Google Scholar 

  4. Plato: Plato’s Republic. Hackett Publishing Company, Indianapolis (1974) Translated by G. M. A. Grube.

    Google Scholar 

  5. Searle, J.: Is the brain a digital computer? In Grim, P., Mar, G., Williams, P., eds.: The Philosopher’s Annual, Atascadero, CA, Ridgeview Publishing Company (1990) Presidential address (American Philosophical Association, 1990).

    Google Scholar 

  6. Choe, Y., Bhamidipati, S.K.: Autonomous acquisition of the meaning of sensory states through sensory-invariance driven action. In Ijspeert, A.J., Murata, M., Wakamiya, N., eds.: Biologically Inspired Approaches to Advanced Information Technology. Lecture Notes in Computer Science 3141, Berlin, Springer (2004) 176–188

    Google Scholar 

  7. Choe, Y., Smith, N.H.: Motion-based autonomous grounding: Inferring external world properties from internal sensory states alone. In Gil, Y., Mooney, R., eds.: Proceedings of the 21st National Conference on Artificial Intelligence. (2006) 936–941.

    Google Scholar 

  8. Llinás, R.R.: I of the Vortex. MIT Press, Cambridge, MA (2001)

    Google Scholar 

  9. Silberman, Y., Miikkulainen, R., Bentin, S.: Semantic effect on episodic associations. Proceedings of the Twenty-Third Annual Conference of the Cognitive Science Society 23 (1996) 934–939

    Google Scholar 

  10. Lashley, K.S.: The problem of serial order in behavior. In Jeffress, L.A., ed.: Cerebral Mechanisms in Behavior. Wiley, New York (1951) 112–146

    Google Scholar 

  11. Moore, F.C.T.: Bergson: Thinking Backwards. Cambridge University Press, Cambridge, UK (1996) Shape Recognition Through Dynamic Motor Representations 209

    Google Scholar 

  12. Bergson, H.: Matter and Memory. Zone Books, New York, NY (1988) Translated by Nancy Margaret Paul and W. Scott Palmer.

    Google Scholar 

  13. Gibson, J.J.: The Perception of the Visual World. Houghton Mifflin, Boston (1950)

    Google Scholar 

  14. Aloimonos, J.Y.,Weiss, I., Bandopadhay, A.: Active vision. International Journal on Computer Vision 1 (1988) 333–356

    CrossRef  Google Scholar 

  15. Bajcsy, R.: Active perception. Proceedings of the IEEE 76 ((1988) 996–1006

    CrossRef  Google Scholar 

  16. Ballard, D.H.: Animate vision. Artificial Intelligence 48 (1991) 57–86

    CrossRef  Google Scholar 

  17. Brooks, R.A.: Intelligence without representation. Artificial Intelligence 47 (1991) 139–159

    CrossRef  Google Scholar 

  18. Hecht, H., Vogt, S., Prinz, W.: Motor learning enhances perceptual judgment: A case for action-perception transfer. Psychological Research 65 (2001) 3–14

    CrossRef  Google Scholar 

  19. Naito, E., Roland, P.E., Ehrsson, H.H.: I felt my hand moving: A new role of the primary motor cortex in somatic perception of limb movement. Neuron 36 (2002) 979–988

    CrossRef  Google Scholar 

  20. Held, R., Hein, A.: Movement-produced stimulation in the development of visually guided behavior. Journal of Comparative and Physiological Psychology 56 (1963) 872–876

    Google Scholar 

  21. Bach y Rita, P.: Brain Mechanisms in Sensory Substitution. Academic Press, New York (1972)

    Google Scholar 

  22. Bach y Rita, P.: Tactile vision substitution: Past and future. International Journal of Neuroscience 19 (1983) 29–36

    CrossRef  Google Scholar 

  23. O’Regan, J.K., No骠A.: A sensorimotor account of vision and visual consciousness. Behavioral and Brain Sciences 24(5) (2001) 883–917

    Google Scholar 

  24. Philipona, D., O’Regan, J.K., Nadal, J.P.: Is there something out there? Inferring space from sensorimotor dependencies. Neural Computation 15 (2003) 2029–2050

    CrossRef  MATH  Google Scholar 

  25. Philipona, D., O’Regan, J.K., Nadal, J.P., Coenen, O.J.M.D.: Perception of the structure of the physical world using unknown multimodal sensors and effectors. In Thrun, S., Saul, L., Schölkopf, B., eds.: Advances in Neural Information Processing Systems 16,Cambridge, MA, MIT Press (2004) 945–952

    Google Scholar 

  26. Humphrey, N.: A History of the Mind. HarperCollins, New York (1992)

    Google Scholar 

  27. Hurley, S.: Perception and action: Alternative views. Synthese 129 (2001) 3–40

    CrossRef  Google Scholar 

  28. Granlund, G.H.: Does vision inveitably have to be active? In: Proceedings of the 11th Scandinavian Conference on Image Analysis. (1999) 11–19

    Google Scholar 

  29. Weng, J., McClelland, J.L., Pentland, A., Sporns, O., Stockman, I., Sur, M., Thelen, E.: Autonomous mental development by robots and animals. Science 291 (2001) 599–600

    CrossRef  Google Scholar 

  30. Lugarella, M., Metta, G., Pfeifer, R., Sandini, G.: Developmental robotics: A survey. Connection Science 15 (2003) 151–190

    CrossRef  Google Scholar 

  31. Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press, Cambridge, MA (1999)

    Google Scholar 

  32. Almássy, N., Sporns, O.: Perceptual invariance and categorization in an embodied model of the visual system. In Webb, B., Consi, T.R., eds.: Biorobotics: Methods and Applications. AAAI Press/MIT Press, Menlo Park, CA (2001) 123–143

    Google Scholar 

  33. Pierce, D.M., Kuipers, B.J.: Map learning with uninterpreted sensors and effectors. Artificial Intelligence 92 (1997) 162–227

    CrossRef  Google Scholar 

  34. Kuipers, B., Beeson, P., Modayil, J., Provost, J.: Bootstrap learning of foundational representations. Connection Science 18 (2006) 145–158

    CrossRef  Google Scholar 

  35. Cohen, P.R., Beal, C.R.: Natural semantics for a mobile robot. In: Proceedings of the European Conferenec on Cognitive Science. (1999)

    Google Scholar 

  36. Beer, R.D.: Dynamical approaches to cognitive science. Trends in Cognitive Sciences 4 (2000) 91–99

    CrossRef  Google Scholar 

  37. Cariani, P.: Symbols and dynamics in the brain. Biosystems 60 (2001) 59–83

    CrossRef  Google Scholar 

  38. Kozma, R., Freeman, W.J.: Basic principles of the KIV model and its application to the navigation problem. Journal of Integrative Neuroscience 2 (2003) 125–145

    CrossRef  Google Scholar 

  39. Varela, F.J., Thompson, E., Rosch, E.: The Embodied Mind: Cognitive Science and Human Experience. MIT Press, Cambridge, MA (1993)

    Google Scholar 

  40. Schaal, S., Ijspeert, A.J., Billard, A.J.: Computational approaches to motor learning by imitation. Philosophical Transactions of the Royal Society: Biological Sciences 358 (2003) 537–547

    CrossRef  Google Scholar 

  41. Billard, A.: Imitation. In Arbib, M.A., ed.: The Handbook of Brain Theory and Neural Networks. 2nd edn. MIT Press, Cambridge, MA (2003) 566–569 210 N. Misra, Y. Choe

    Google Scholar 

  42. Breazeal, C., Scassellati, B.: Robots that imitate humans. Trends in Cognitive Sciences 6 (2002) 481–487

    CrossRef  Google Scholar 

  43. Rao, R.P.N., Shon, A.P., Meltzoff, A.N.: A bayesian model of imitation in infants and robots. Cambridge University Press, Cambridge, UK (2004) In press.

    Google Scholar 

  44. MatariĆ, M.J.: Sensory-motor primitives as a basis for imitation: Linking perception to action and biology to robotics. In Dautenhahn, K., Nehaniv, C., eds.: Imitation in Animals and Artifacts. MIT Press, Cambridge, MA (2001) 391–422

    Google Scholar 

  45. Billard, A., Matari, M.J.: A biologically inspired robotic model for learning by imitation. In: International Conference on Autonomous Agents: Proceedings of the Fourth International Conference on Autonomous Agents, New York, ACM Press (2000) 373–380

    Google Scholar 

  46. Ikegami, T., Taiji, M.: Imitation and cooperation in coupled dynamical recognizers. In: Proceedings of the 5th European Conference on Advances in Artificial Life: Lecture Notes in Computer Science 1674. Springer, London (1999) 545–554

    Google Scholar 

  47. Ito, M., Tani, J.: On-line imitative interaction with a humanoid robot using a dynamic neural network model of a mirror system. Adaptive Behavior 12 (2004) 93–115

    CrossRef  Google Scholar 

  48. Wyss, R.,Künig, P., Verschure, P.F.M.J.: A model of the ventral visual system based on temporal stability and local memory. PLoS Biology 4 (2006) e120

    CrossRef  Google Scholar 

  49. Floreano, D., Suzuki, M., , Mattiussi, C.: Active vision and receptive field development in evolutionary robots. Evolutionary Computation 13 (2005) 527–544

    CrossRef  Google Scholar 

  50. Lungarella, M., Sporns, O.: Mapping information flow in sensorimotor networks. PLoS Computaitonal Biology 2 (2006) 1301–1312

    Google Scholar 

  51. Bongard, J., Zykov, V., Lipson, H.: Reslient machines through continuous self-modeling. Science 314 (2006) 1118–1121

    CrossRef  Google Scholar 

  52. Freeman, W.J.: A neurobiological theory of meaning in perception. In: Proceedings of the International Joint Conference on Neural Networks, IEEE (2003) 1373–1378

    Google Scholar 

  53. Ziemke, T., Sharkey, N.E.: A stroll through the worlds of robots and animals: Applying Jakob von Uexküllș theory of meaning to adaptive robots and artificial life. Semiotica 134 (2001) 701–746

    CrossRef  Google Scholar 

  54. Abelson, H.: LOGO for the Apple II. 1st edn. McGraw-Hill, Peterborough, N.H. (1982)

    Google Scholar 

  55. Werbos, P.J.: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD thesis, Department of Applied Mathematics, Harvard University, Cambridge, MA (1974)

    Google Scholar 

  56. Rumelhart, D.E., McClelland, J.L., eds.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations. MIT Press, Cambridge, MA (1986)

    Google Scholar 

  57. Werbos, P.J.: Backpropagation through time: What it does and how to do it. Proceedings of the IEEE 78 (1990) 1550–1560

    CrossRef  Google Scholar 

  58. Press,W.H., Teukolsky, S.A., Vetterling,W.T., Flannery, B.P.: Numerical Recipes in C. Second edn. Cambridge University Press (1992)

    Google Scholar 

  59. Conditt, M.A., Mussa-Ivaldi, F.A.: Central representation of time during motor learning. Journal of Neurobiology 20 (1999) 11625–11630

    Google Scholar 

  60. Tulving, E., Markowitsch, H.J.: Episodic and declarative memory: role of the hippocampus. Hippocampus 8 (1996) 198–204

    CrossRef  Google Scholar 

  61. Buckner, R.L.: Neural origins of ’i remember’. Nature Neuroscience 3 (2000) 1068–1069

    CrossRef  Google Scholar 

  62. Wise, S.P.: The role of the basal ganglia in procedural memory. Seminars in Neuroscience 8 (1996) 39–46

    CrossRef  Google Scholar 

  63. Humphrey, N.: Seeing Red. Harvard University Press, Cambridge, MA (2006)

    Google Scholar 

  64. Misra, N.: Comparison of motor-based versus visual representations in object recognition tasks. Master’s thesis, Department of Computer Science, Texas A&M University, College Station, Texas (2005)

    Google Scholar 

Download references

Authors
  1. Navendu Misra
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yoonsuck Choe
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. School of Engineering and Applied Sciences, Harvard University, 33 Oxford St, Cambridge, MA 02138, USA

    Leonid I. Perlovsky

  2. Computational Neurodynamics Laboratory 373 Dunn Hall, Department of Computer Science University of Memphis, Memphis, TN 38152, USA

    Robert Kozma

Rights and permissions

Reprints and Permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Misra, N., Choe, Y. (2007). Shape Recognition Through Dynamic Motor Representations. In: Perlovsky, L.I., Kozma, R. (eds) Neurodynamics of Cognition and Consciousness. Understanding Complex Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73267-9_9

Download citation

Publish with us

Policies and ethics

search

Navigation