Experimenting and theorizing in theory formation
ISMIS '86 Proceedings of the ACM SIGART international symposium on Methodologies for intelligent systems
Scientific discovery: computational explorations of the creative process
Scientific discovery: computational explorations of the creative process
Artificial Intelligence
Discovering admissible simultaneous equations of large scale systems
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Determining Arguments of Invariant Functional Descriptions
Machine Learning
Discovering admissible models of complex systems based on scale-types and identity constraints
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Computer Assisted Discovery of First Principle Equations from Numeric Data (Abstract)
PAKDD '99 Proceedings of the Third Pacific-Asia Conference on Methodologies for Knowledge Discovery and Data Mining
| Hi-index | 0.01 |
SDS2 is a system to discover and identify the quantitative model consisting of simultaneous equations reflecting the first principles underlying the objective process through experiments. It consists of SSF and SDS, where the former is to discover the structure of the simultaneous equations and the latter to discover a quantitative formula of each complete equation. The power of SDS2 comes from the use of the complete subset structure in a set of simultaneous equations, the scale-types of the measurement data and the mathematical property of identity by which to constrain the admissible solutions. The basic principles, algorithms and implementation of SDS2 are described, and its efficiency and practicality are demonstrated and discussed with large scale working examples.