A creative abduction approach to scientific and knowledge discovery

Authors:
H. Prendinger;M. Ishizuka
Affiliations:
National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan;Department of Information and Communication Engineering, Graduate School of Information Science and Technology, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
Venue:
Knowledge-Based Systems
Year:
2005

Citing 8
Cited 2

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic Horn abduction and Bayesian networks

Artificial Intelligence
Fab: content-based, collaborative recommendation

Communications of the ACM
Networked bubbled propagation: a polynomial-time hypothetical reasoning method for computing near-optimal solutions

Artificial Intelligence - Special issue: artificial intelligence research in Japan
Adaptive Web sites: automatically synthesizing Web pages

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Qualifying the expressivity/efficiency tradeoff: reformation-based diagnosis

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Inductive Logic Programming: Techniques and Applications

Inductive Logic Programming: Techniques and Applications
Principles of human-computer collaboration for knowledge discovery in science

Artificial Intelligence

Concept discovery on relational databases: New techniques for search space pruning and rule quality improvement

Knowledge-Based Systems
Towards group behavioral reason mining

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we explore the range of applicability of abductive reasoning for knowledge discovery. In particular, we discuss a novel form of abduction, called creative abduction, where new knowledge is generated in the process of explaining observed events, and demonstrate its relevance to knowledge discovery. The main contribution of this paper is twofold: First, we show that creative abduction can be used to infer a disposition explaining local temporal regularities. In the presence of multiple correlated regularities, this form abduction may significantly unify a given corpus of knowledge, corresponding to theory formation in scientific discovery. Second, we present a weaker form of creative abduction that infers a goal (e.g. interest) from simple 'condition-effect' rules called 'transitions'. If multiple transitions are correlated, the weaker form of creative abduction can be used to identify, e.g. clusters of Web users, as done in Web usage mining. We will focus on the formal underpinnings of this new form of abduction that seems readily applicable to a wide range of practical knowledge discovery problems.