GPU-based implementation of a cerebellar spiking network model for realtime robot control
RIKEN BSI-TOYOTA Collaboration Center, RIKEN Brain Science Institute
The 21st Annual Conference of the Japanese Neural Network Society, 2011
We implemented a large-scale cerebellar cortical model composed of more than 100,000 spiking neuron units on a Graphics Processing Unit (GPU). We carried out computer simulations of the model in realtime. We adopted the model to online learning of timing for a humanoid robot.
January 17, 2012 by hgpu
