Efficient online learning with Spiral Recurrent Neural Networks

Distributed intelligent systems like self-organizing wireless sensor and actuator networks are supposed to work mostly autonomous even under changing environmental conditions. This requires robust and efficient self-learning capabilities implementable on embedded systems with limited memory and comp...

Full description

Saved in:
Bibliographic Details
Main Authors: Sollacher, R., Huaien Gao
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Covariance matrix
Neurons
Recurrent neural networks
Time series analysis
Training
Trajectory
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Distributed intelligent systems like self-organizing wireless sensor and actuator networks are supposed to work mostly autonomous even under changing environmental conditions. This requires robust and efficient self-learning capabilities implementable on embedded systems with limited memory and computational power. We present a new solution called spiral recurrent neural networks with an online learning based on an extended Kalman filter and gradients as in real-time recurrent learning. We illustrate its performance using artificial and real-life time series and compare it to other approaches. Finally we describe a few potential applications.
ISSN:2161-4393
1522-4899
2161-4407
DOI:10.1109/IJCNN.2008.4634155