Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives

Junpei Zhong, Angelo Cangelosi, Stefan Wermter

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

The acquisition of symbolic and linguistic representations of sensorimotor behavior is a cognitive process performed by an agent when it is executing and/or observing own and others' actions. According to Piaget's theory of cognitive development, these representations develop during the sensorimotor stage and the pre-operational stage. We propose a model that relates the conceptualization of the higher-level information from visual stimuli to the development of ventral/dorsal visual streams. This model employs neural network architecture incorporating a predictive sensory module based on an RNNPB (Recurrent Neural Network with Parametric Biases) and a horizontal product model. We exemplify this model through a robot passively observing an object to learn its features and movements. During the learning process of observing sensorimotor primitives, i.e., observing a set of trajectories of arm movements and its oriented object features, the pre-symbolic representation is self-organized in the parametric units. These representational units act as bifurcation parameters, guiding the robot to recognize and predict various learned sensorimotor primitives. The pre-symbolic representation also accounts for the learning of sensorimotor primitives in a latent learning context.

Original languageEnglish
Article number22
JournalFrontiers in Behavioral Neuroscience
Volume8
Issue numberFEB
DOIs
Publication statusPublished - 2014 Feb 4
Externally publishedYes

Keywords

  • Horizontal product
  • Parametric biases
  • Pre-symbolic communication
  • Recurrent neural networks
  • Sensorimotor integration

ASJC Scopus subject areas

  • Behavioral Neuroscience
  • Cognitive Neuroscience
  • Neuropsychology and Physiological Psychology

Fingerprint Dive into the research topics of 'Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives'. Together they form a unique fingerprint.

  • Cite this