Multiple Time Scales Recurrent Neural Network for Complex Action Acquisition

Martin Peniak, Davide Marocco, Jun Taniy, Yuichi Yamashitay, Kerstin Fischerz, Angelo Cangelosi
The University of Plymouth, Drake Circus, Plymouth, PL4 8AA, United Kingdom
International Joint Conference on Development and Learning (ICDL) and Epigenetic Robotics (ICDL-EPIROB), 2011


   title={Multiple time scales recurrent neural network for complex action acquisition},

   author={Peniak, Martin and Marocco, Davide and Tani, Jun and Yamashita, Yuichi and Fischer, Kerstin and Cangelosi, Angelo},

   journal={Proceedings of ICDL-Epirob},



Download Download (PDF)   View View   Source Source   Source codes Source codes




This paper presents novel results of complex action learning experiments based on the use of extended multiple time-scales recurrent neural networks (MTRNN). The experiments were carried out with the iCub humanoid robot, as a model of the developmental learning of motor primitives as the basis of sensorimotor and linguistic compositionality. The model was implemented through the Aquila cognitive robotics toolkit, which supports the CUDA architecture and makes use of massively parallel GPUs (graphics processing units). The 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 using large-scale MTRNNs. This forms the basis on ongoing experiments on action and language compositionality.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: