Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6865618 | Neurocomputing | 2015 | 7 Pages |
Abstract
A novel dual-task learning approach based on recurrent neural networks with factored tensor components for system identification tasks is presented. The goal is to identify the dynamics of a system given few observations which are augmented by auxiliary data from a similar system. The problem is motivated by real-world use cases and a mathematical problem description is given. Further, our proposed model-the factored tensor recurrent neural network (FTRNN)-and two alternative models are introduced which are benchmarked on the cart-pole and mountain car simulations. We show that the FTRNN consistently and significantly outperformed the competing models in accuracy and data-efficiency.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Alexander Hentschel, Thomas Runkler,