This paper concerns the assessment of linear cause-effect relationships from a combination of observational data and qualitative causal structures. The paper shows how techniques developed for identifying causal effects in causal Bayesian networks can be used to identify linear causal effects, and thus provides a new approach for assessing linear causal effects in structural equation models. Us...

Causation plays a critical role in many predictive and inference tasks. Bayesian networks (BNs) have been used to construct inference systems for diagnostics and decision making. More recently, fuzzy cognitive maps (FCMs) have gained considerable attention and offer an alternative framework for representing structured human knowledge and causal inference. In this paper I briefly introduce Bayes...

Two layer causal networks are limited for representing real diagnostic problems. In this paper, a neural network diagnosis method based on a multiple layer causal network is proposed. Multiple layer networks have the power to represent complex diagnostic problems. Therefore, the method proposed in this paper is more practical for real world diagnostic problem solving than the method proposed in...

We present a general-purpose method for the optimization of quantum networks, including both causal networks and networks with indefinite causal structure. Our method applies to a broad class of performance measures, defined operationally in terms of tests set up by a verifier. We show that the optimal performance can be quantified by the max relative entropy between a suitable operator, associ...

Bayesian networks are limited in differentiating between causal and spurious relationships among decision factors. Decision making without differentiating the two relationships cannot be effective. To overcome this limitation of Bayesian networks, this study proposes linking Bayesian networks to structural equation modeling (SEM), which has an advantage in testing causal relationships between f...