Advertisement

Artificial Neural Networks Predicting the Outcome of a Throwing Task – Effects of Input Quantity and Quality

  • Michael Joch
  • Jörg M. Jäger
  • Heiko Maurer
  • Lisa K. Maurer
  • Hermann Müller
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 663)

Abstract

Internal forward models are used to explain motor prediction processes in motor control and learning e.g. predicting an upcoming miss in a throwing task before the knowledge of results is available. In this study we used artificial neural networks (ANN) to model such movement outcome prediction processes. Additionally, we varied the inputs of four different multilayer perceptrons (MLP) with respect to the quantity and the reliability (quality) of input parameters to account for perceptual noise. The results show that ANNs are able to learn the non-linear input-output mapping underlying the throwing task even with few input variables (velocity and angle at ball release). Results improve when providing additional information about the ball flight (prediction accuracy increases from RMSE = 7.9 mm to RMSE = 3.9 mm). However, when a model is provided with noisy inputs only, model training and prediction suffers substantially (RMSE = 53.8 mm). Yet, additional reliable information about the ball flight (in addition to noisy velocity and angle) leads to very high model prediction accuracy again (RMSE = 4.1 mm). In a nutshell, ANNs can be used to model internal forward model predictions, but the availability of reliable input information is essential at least to some extent.

Keywords

Skittles Multilayer perceptron Task performance prediction Forward model Motor control 

Notes

Acknowledgements

This research was supported by the Deutsche Forschungsgemeinschaft funded Collaborative Research Center on “Cardinal Mechanisms of Perception” Grant SFB-TRR 135 and research project MU 1374/3-1.

References

  1. 1.
    Miall, R.C., Wolpert, D.M.: Forward models for physiological motor control. Neural Netw. 9, 1265–1279 (1996)CrossRefzbMATHGoogle Scholar
  2. 2.
    Diedrichsen, J., White, O., Newman, D., Lally, N.: Use-dependent and error-based learning of motor behaviors. J. Neurosci. 30, 5159–5166 (2010)CrossRefGoogle Scholar
  3. 3.
    Schmidt, R., Lee, T.: Motor control and learning: a behavioral emphasis. Human Kinetics, Champaign, IL (2011)Google Scholar
  4. 4.
    Maurer, L.K., Maurer, H., Müller, H.: Neural correlates of error prediction in a complex motor task. Front. Behav. Neurosci. 9, 209 (2015)CrossRefGoogle Scholar
  5. 5.
    Wolpert, D.M., Ghahramani, Z., Jordan, M.I.: An internal model for sensorimotor integration. Science 269, 1880–1882 (1995)CrossRefGoogle Scholar
  6. 6.
    Kawato, M.: Internal models for motor control and trajectory planning. Curr. Opin. Neurobiol. 9, 718–727 (1999)CrossRefGoogle Scholar
  7. 7.
    Wolpert, D.M., Miall, R.C., Kawato, M.: Internal models in the cerebellum. Trends Cogn. Sci. 2, 338–347 (1998)CrossRefGoogle Scholar
  8. 8.
    Jordan, M.I., Rumelhart, D.E.: Forward models: supervised learning with a distal teacher. Cogn. Sci. 16, 307–354 (1992)CrossRefGoogle Scholar
  9. 9.
    Welch, R., Warren, D.: Intersensory interactions. In: Boff, K.R., Kaufman, L., Thomas, J.P. (eds.) Handbook of Perception and Human Performance, pp. 25.1–25.36. Wiley, New York (1986)Google Scholar
  10. 10.
    Krigolson, O.E., Holroyd, C.B.: Hierarchical error processing: different errors, different systems. Brain Res. 1155, 70–80 (2007)CrossRefGoogle Scholar
  11. 11.
    Falkenstein, M., Hohnsbein, J., Hoormann, J., Blanke, L.: Effects of crossmodal divided attention on late ERP components. II. Error processing in choice reaction tasks. Electroencephalogr. Clin. Neurophysiol. 78, 447–455 (1991)CrossRefGoogle Scholar
  12. 12.
    Wolpert, D.M., Flanagan, J.R.: Motor prediction. Curr. Biol. 11, 729–732 (2001)CrossRefGoogle Scholar
  13. 13.
    Haykin, S.: Neural Networks - A Comprehensive Foundation. Prentice Hall, London (1994)zbMATHGoogle Scholar
  14. 14.
    Schöllhorn, W.I., Jäger, J.M., Janssen, D.: Artificial neural network models of sports motions. In: Handbook of Biomechanics and Human Movement Science, pp. 50–64. Routledge, New York City (2008)Google Scholar
  15. 15.
    Kruse, R., Borgelt, C., Braune, C., Mostaghim, S., Steinbrecher, M.: Computational intelligence. Springer, London (2016)CrossRefzbMATHGoogle Scholar
  16. 16.
    Sternad, D., Huber, M.E., Kuznetsov, N.: Acquisition of novel and complex motor skills: stable solutions where intrinsic noise matters less. In: Levin, M.F. (ed.) Progress in Motor Control. Skill Learning, Performance, Health, and Injury, pp. 101–124. Springer, New York (2014)Google Scholar
  17. 17.
    Müller, H., Sternad, D.: Decomposition of variability in the execution of goal-oriented tasks: three components of skill improvement. J. Exp. Psychol. Hum. Percept. Perform. 30, 212–233 (2004)CrossRefGoogle Scholar
  18. 18.
    Adams, L.: Bestimmung der Wahrnehmungsschwelle des motorischen Rauschens bei Zielwurfbewegungen. Unpublished thesis Justus-Liebig-University Giessen (2008)Google Scholar
  19. 19.
    Ernst, M.O., Banks, M.S.: Humans integrate visual and haptic information in a statistically optimal fashion. Nature 415, 429–433 (2002)CrossRefGoogle Scholar
  20. 20.
    Günther, F., Fritsch, S.: neuralnet: training of neural networks. R J. 2, 30–38 (2010)Google Scholar
  21. 21.
    Adams, J.A.: The second facet of forgetting: a review of warm-up decrement. Psychol. Bull. 58, 257–273 (1961)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Michael Joch
    • 1
  • Jörg M. Jäger
    • 1
  • Heiko Maurer
    • 1
  • Lisa K. Maurer
    • 1
  • Hermann Müller
    • 1
  1. 1.Neuromotor Behavior Laboratory, Department of Psychology and Sport ScienceJustus-Liebig-UniversityGiessenGermany

Personalised recommendations