Bayesian networks (BN) are particularly well suited to capturing vague and uncertain knowledge. However, the capture of this knowledge and associated reasoning from human domain experts often requires specialized knowledge engineers and computational modelers responsible for creating BN-based models. Through our experiences in applying BN modeling techniques across application domains, we have analyzed how these models are constructed, refined, and validated with domain experts. From this analysis, we have identified potential simplifying assumptions and used these to guide the design of computational and user interface methods that support the rapid creation and validation of BN models.

Abstract not found

A pervasive feature of the sciences, particularly the applied sciences, is an experimental focus on a few (often only one) possible causal connections. At the same time, scientists often advance and apply relatively broad models that incorporate many different causal mechanisms. We are naturally led to ask whether there are normative rules for integrating multiple local experimental conclusions into models covering many additional variables. In this paper, we provide a positive answer to this question by developing several inference rules that use local causal models to place constraints on the integrated model, given quite general assumptions. We also demonstrate the practical value of these rules by applying them to a case study from ecology. 1 Experimental scope in applied sciences 2 Fusing the results of experiments 3 A concrete example of the inference rules 4 Application to a case study 1 Experimental scope in applied sciences Total photosynthetic material has increased globally in recent years (though with local decreases), and one might naturally wonder why. In a recent paper in Science, Nemani et al. ([2003]) focused on some of the potential causes of global vegetation growth during the past 20 years. Their analysis focused on only four variables: growing season average temperature, vapor pressure deficit, solar radiation, and net primary production (photosynthetic material). Their study considered only a limited variable set because of (a) the global scale of their analysis, and (b) the relatively long study period (18 years). Despite this limited scope (in terms of variables), their study gives substantial support to the hypothesis that the first three variables are causes of the last, and helps to clarify the functional form of those dependencies. At the same time, they explicitly note that there are many causally relevant variables that were ignored in their study, such as vegetation

We describe a novel noisy-logical distribution for representing the distribution of a binary output variable conditioned on multiple binary input variables. The distribution is represented in terms of noisy-or’s and noisy-and-not’s of causal features which are conjunctions of the binary inputs. The standard noisy-or and noisy-andnot models, used in causal reasoning and artificial intelligence, are special cases of the noisy-logical distribution. We prove that the noisy-logical distribution is complete in the sense that it can represent all conditional distributions provided a sufficient number of causal factors are used. We illustrate the noisy-logical distribution by showing that it can account for new experimental findings on how humans perform causal reasoning in complex contexts. We speculate on the use of the noisy-logical distribution for causal reasoning and artificial intelligence. 1

This paper is twofold. First, we present a new method for collective intention recognition based on mainstream philosophical accounts. Second, we extend our previous Elder Care system with collective intention recognition ability for assisting a couple of elderly people. The previous system was just capable of individual intention recognition, and so it has now been enabled to deal with situations where the elders intend to do things together. 1.

Functional magnetic resonance imaging (fMRI) was used to examine the neural correlates of perceptual causality. Participants were imaged while viewing alternating blocks of causal events in which a ball collides with, and causes movement of another ball, versus non-causal events in which a spatial or a temporal gap precedes the movement of a second ball. There were significantly higher levels of relative activation in the right middle frontal gyrus and the right inferior parietal lobule for causal relative to non-causal events. Furthermore, when the differential effects of spatial and temporal incontiguities were subtracted from the contiguous stimuli, we observed both common (right prefrontal) and unique (right parietal and right temporal) regions of activation as a function of spatial and temporal processing of contiguity, respectively. Taken together, these data provide a means to help determine how the visual system extracts causality from dynamic visual information in the environment using spatial and temporal cues. D 2004 Elsevier B.V. All rights reserved.

Competence and performance in causal learning The dominant theoretical approach to causal learning postulates the acquisition of associative weights between cues and outcomes. These associative weights reflect the amount of covariation between the learning events. In the past few years, the associationist approach to causal learning has been criticized by a number of researchers

A normative framework for modeling causal and counterfactual reasoning has been proposed by Spirtes, Glymour, and Scheines (1993; cf. Pearl, 2000). The framework takes as fundamental that reasoning from observation and intervention differ. Intervention includes actual manipulation as well as counterfactual manipulation of a model via thought. To represent intervention, Pearl employed the do operator that simplifies the structure of a causal model by disconnecting an intervened-on variable from its normal causes. Construing the do operator as a psychological function affords predictions about how people reason when asked counterfactual questions about causal relations that we refer to as undoing, a family of effects that derive from the claim that intervened-on variables become independent of their normal causes. Six studies support the prediction for causal (A causes B) arguments but not consistently for parallel conditional (if A then B) ones. Two of the studies show that effects are treated as diagnostic when their values are observed but nondiagnostic when they are intervened on. These results cannot be explained by theories that do not distinguish interventions from other sorts of events.

We propose that function is a complex relational concept that draws on many conceptual domains for its content. According to the HIPE theory, these domains include History, Intentional perspective, the Physical environment, and Event sequences. The function of a particular entity does not have a single sense. Instead many different senses can be constructed that depend on the conceptualizer's current goal, setting, and personal history. On a given occasion, relevant knowledge is assembled across conceptual domains to construct a relevant sense, represented as a mental simulation and structured by a causal chain.

Abstract. The human mind has been designed to evaluate similarity fast and efficiently. When building/using a data format to make the web content more machine-friendly, can we learn something useful from how the mind represents data? We present four theories psychological theories that tried to solve the problem and how they relate to semantic web practices. Metric models (such as the vector space model and LSA) were the first-comers and still have important advantages. Advances in Bayesian methods pushed Feature models ( e.g., Topic model). Structural mapping models propose that for similarity, shared structure matters more, although the formalisms that express these ideas are still developing. Transformational distance models (e.g., syntagmatic-paradigmatic-SP- model) reduce similarity to information transmission. Topic and SP models do not require preexisting classes but still have a long way to go; the need of automatically generating structure is less pressing when one of the driving forces of the semantic web is the creation of ontologies.