Multiple Time Scales Recurrent Neural Network for Complex Action Acquisition

This paper presents preliminary results of complex action learning based on a multiple time-scales recurrent neural network (MTRNN) model embodied in the iCub humanoid robot. The model was implemented as part of Aquila cognitive robotics toolkit and accelerated through the compute unified device architecture (CUDA) making use of massively parallel GPU (graphics processing unit) devices that significantly outperform standard CPU processors on parallel tasks. The preliminary results presented herein show that the model was able to learn and successfully reproduce multiple behavioural sequences of actions in an object manipulation task scenario.