The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences

Matthieu Lagarde (1) , Pierre Andry (1) , Philippe Gaussier (1)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes

We present an artificial neural network used to learn online complex temporal sequences of gestures to a robot. The system is based on a simple temporal sequences learning architecture, neurobiological inspired model using some of the properties of the cerebellum and the hippocampus, plus a diversity generator composed of CTRNN oscillators. The use of oscillators allows to remove the ambiguity of complex sequences. The associations with oscillators allow to build an internal state to disambiguate the observable state. To understand the effect of this learning mechanism, we compare the performance of (i) our model with (ii) simple sequence learning model and with (iii) the simple sequence learning model plus a competitive mechanism between inputs and oscillators. Finally, we present an experiment showing a AIBO robot, which learns and reproduces a sequence of gestures.

Mots clés: complex temporal sequence; robotics; artificial neural networks

Domaines: Informatique

Matthieu Lagarde, Pierre Andry, Philippe Gaussier. The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences. 2007. ⟨hal-00356671⟩