Vector field approximation by model inclusive learning of neural networks

Authors:
Yasuaki Kuroe;Hajimu Kawakami
Affiliations:
Department of Information Science, Kyoto Institute of Technology, Kyoto, Japan;Department of Electronics and Informatics, Ryukoku University, Ohtsu, Japan
Venue:
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Year:
2007

Citing 1
Cited 3

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1

Neural-Net Based Modeling of Velocity and Concentration Fields

Journal of Visualization
Estimation Method of Motion Fields from Images by Model Inclusive Learning of Neural Networks

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
A physics-driven neural networks-based simulation system (phynness) for multimodal interactive virtual environments involving nonlinear deformable objects

Presence: Teleoperators and Virtual Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

The problem of vector field approximation arises in the wide range of fields such as motion control, computer vision and so on. This paper proposes a method for reconstructing an entire continuous vector field from a sparse set of sample data by training neural networks. In order to make approximation results possess inherent properties of vector fields and to attain reasonable approximation accuracy with computational efficiency, we include a priori knowledge on inherent properties of vector fields into the learning problem of neural networks, which we call model inclusive learning. An efficient learning algorithm of neural networks is derived. It is shown through numerical experiments that the proposed method makes it possible to reconstruct vector fields accurately and efficiently.