Orientation-dependent effects in neural networks

  • Michele Voltolina
  • Carlo Umilta'
Part II The Quest of Perceptual Primitives
Part of the Lecture Notes in Computer Science book series (LNCS, volume 745)


When human observers decide whether disoriented patterns are normal or reflected (mirror images), response time increases with orientational disparity from the upright. This orientation-dependent effect was obtained with a 4-layer neural network and a back-propagation algorithm. In the learning phase of Experiment 1, the network learned to classify normal-reflected patterns that could appear at different orientations on an input grid. In the test phase, the same patterns were presented at new orientations. Fewer trials were required to re-learn the classification when the patterns were closer to the upright. In Experiment 2, the same network was presented with new patterns. Fewer trials were again required to learn the classification when the patterns were closer to the upright.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    S. Bagnara, F. Simion, C. Umilia': Reference patterns and the process of normalization. Perception & Psychophysics, 35, 186–192 (1984)Google Scholar
  2. 2.
    J.D. Cohen, K. Dunbar, J.L. McClelland: On the control of automatic processes: A parallel distributed processing account of the Stroop effect. Psychological Review, 97, 332–361 (1990)PubMedGoogle Scholar
  3. 3.
    M.C. Corballis, M.C. (1988). Recognition of disordered shapes. Psychological Review, 95, 201–211 (1988)Google Scholar
  4. 4.
    P. Jolicour: Orientation congruency effects on the identification of disoriented shapes. Journal of Experimental Psychology: Human Perception and Performance, 16, 351–364 (1990)Google Scholar
  5. 5.
    A. Koriat, J. Norman: Frames and images: Sequential effects in mental rotation. Journal of Experimental Psychology: Learning, Memory, and Cognition, 14, 93–111 (1988)Google Scholar
  6. 6.
    A. Koriat, J. Norman, R. Kimchi: Recognition of rotated letters: Extracting invariance across successive and simultaneous stimuli. Journal of Experimental Pychology: Human Perception and Performance, 7, 444–457 (1991)Google Scholar
  7. 7.
    J.M.J. Murre: Learning and categorization in modular neural networks. New York: Harvester/Wheatsheaf 1992Google Scholar
  8. 8.
    M. Moscovitch, C. Umilta': Conscious and nonconscious aspects of memory: A neuropsychological framework of modules and central systems. In: R.G. Lister, H.J. Weingartner (eds.): Perspective on cognitive neuroscience. Oxford: Oxford University Press 1991Google Scholar
  9. 9.
    J.G. Rucckl, K.R. Cave, S.M. Kosslyn: Why are “what” and “where” processed by separate cortical visual systems? A computational investigation. Journal of Cognitive Neuroscience, 1, 171–186 (1989)Google Scholar
  10. 10.
    D.E. Rumelhart, G. Hinton, R. Williams: Learning internal representations by error propagation. In: D.E. Rumelhart, J.L. McClelland (eds.): Parallel distributed processing: Explorations in the microstructure of cognition. Volume I: Foundations. Cambridge, MA: MIT Press 1986Google Scholar
  11. 11.
    R.N. Shepard, L.A. Cooper: Mental images and their transformations. Cambridge, MA: MIT Press 1982Google Scholar
  12. 12.
    F. Simion, S. Bagnara, S. Roncato, C. Umilta': Transfomation processes upon the visual code. Perception & Psychophysics, 31, 13–25 (1982)Google Scholar
  13. 13.
    M. Voltolina, C. Umilta', G. Sarlori: Simulazione su rete neurale del fenomeno delle rotazioni mentali. In: G. Adorni, W. Gerbino, V. Roberto (eds.): I sensi dell'automa. Trieste: LINT 1992Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Michele Voltolina
    • 1
  • Carlo Umilta'
    • 1
  1. 1.Dipartimento di Psicologia GeneraleUniversita' di PadovaPadovaItaly

Personalised recommendations