A Fast Training Algorithm of Multiple-Timescale Recurrent Neural Network for Agent Motion Generation

Motion understanding and regeneration are two basic aspects of human-agent interaction. One important function of agents is to represent human's activities. For better interaction with human, robot agents should not only do something following human's order, but also be able to understand or even play some actions. Multiple Timescale Recurrent Neural Networks (MTRNN) is believed to be an efficient tool for robots action generation. In our previous work, we extended the concept of MTRNN and developed Supervised MTRNN for motion recognition. In this paper, we use Conditional Restricted Boltzmann Machine (CRBM) to initialize Supervised MTRNN and accelerate the training speed of Supervised MTRNN. Experiment results show that our method can greatly increase the training speed without losing much performance.