2009 Special Issue: Cross-modal and scale-free action representations through enaction

  • Authors:
  • Alex Pitti;Hassan Alirezaei;Yasuo Kuniyoshi

  • Affiliations:
  • ERATO Synergistic Intelligence Project, JST, The University of Tokyo, 113-8656 Tokyo, Japan;ISI Laboratory, Department of Mechano-Informatics, The University of Tokyo, 113-8656 Tokyo, Japan;ERATO Synergistic Intelligence Project, JST, The University of Tokyo, 113-8656 Tokyo, Japan and ISI Laboratory, Department of Mechano-Informatics, The University of Tokyo, 113-8656 Tokyo, Japan

  • Venue:
  • Neural Networks
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Embodied action representation and action understanding are the first steps to understand what it means to communicate. We present a biologically plausible mechanism to the representation and the recognition of actions in a neural network with spiking neurons based on the learning mechanism of spike-timing-dependent plasticity (STDP). We show how grasping is represented through the multi-modal integration between the vision and tactile maps across multiple temporal scales. The network evolves into a small-world organization with scale-free dynamics promoting efficient inter-modal binding of the neural assemblies with accurate timing. Finally, it acquires the qualitative properties of the mirror neuron system to trigger an observed action performed by someone else.