Discovering time differential law equations containing hidden state variables and chaotic dynamics

Authors:
Takashi Washio;Fuminori Adachi;Hiroshi Motoda
Affiliations:
Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan;Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan;Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan
Venue:
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Year:
2005

Citing 7
Cited 0

Scientific discovery: computational explorations of the creative process

Scientific discovery: computational explorations of the creative process
Kalman Filtering and Neural Networks

Kalman Filtering and Neural Networks
Global solutions for nonlinear systems using qualitative reasoning

Annals of Mathematics and Artificial Intelligence
On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Integrating Quantitative and Qualitative Discovery: The ABACUS System

Machine Learning
Declarative Bias in Equation Discovery

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Discovering Admissible Model Equations from Observed Data Based on Scale-Types and Identity Constrains

IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel approach to discover simultaneous time differential law equations having high plausibility to represent first principles underlying objective processes. The approach has the power to identify law equations containing hidden state variables and/or representing chaotic dynamics without using any detailed domain knowledge.