In the light of recent developments in computer technology, a promising and efficient way to design a material with a desired property would be to solve the inverse problem: use a physical property to predict structure. Here, we discuss the basic idea and mathematical foundation of the inverse approach, and proposed strategies for its utilization in the design of materials over nano‐ to macro‐scales. At the nano‐scale, analyzed strategies include scanning of a high‐dimensional space of chemical compounds for those compounds that have a targeted property, and identification of correlations in large databases of materials. However, unlike utilization of inverse approach at nano‐scale where full structural information ‐ atoms and their positions‐ is linked to targeted properties, at the meso‐ and macro‐scale, only partial structural information, manifested via structural motifs or representative volume elements, is available. We discuss the role of partial structural information in the inverse approach to the design of materials at those scales. Risks and limitations of the inverse approach are analyzed and dependence of the approach on factors such as structure parametrization, approximations in theoretical models, and feedback from structural characterization, is addressed.
When constructing Bayesian networks with domain experts, network engineers often use the noisy-OR model, and causal interaction models more generally, to alleviate the burden of probability elicitation: the use of such a model serves to reduce the number of probabilities to be elicited on the one hand, and on the other hand forestalls experts having to give assessments for probabilities with compound conditions which they feel are hard to envision. Recently, we have shown that ill-considered use of the noisy-OR model specifically can substantially decrease a network's performance, especially in domains in which causal mechanisms include cancellation effects. Motivated by this observation, we designed a new causal interaction model, with the same engineering advantages as the noisy-OR model, to describe such effects. We detail properties of our intercausal cancellation model, and compare it against existing causal interaction models. We further illustrate the application of our model in the real-world domain of pharmacology. 相似文献
Recognising everyday activities including information about the context requires to handle large state spaces. The usage of wearable sensors like six degree of freedom accelerometers increases complexity even more. Common approaches are unable to maintain an accurate belief state within such complex domains. We show how marginal filtering can overcome limitations of standard particle filtering and efficiently infer the context of actions. Symbolic models of human behaviour are used to recognise activities in two different settings with different state space sizes. Based on these scenarios we compare the marginal filter to the standard particle filter. An evaluation shows that the marginal filter performs comparably in small state spaces but outperforms the particle filter in large state spaces. 相似文献
Traditionally, Hawkes processes are used to model time-continuous point processes with history dependence. Here, we propose an extended model where the self-effects are of both excitatory and inhibitory types and follow a Gaussian Process. Whereas previous work either relies on a less flexible parameterization of the model, or requires a large amount of data, our formulation allows for both a flexible model and learning when data are scarce. We continue the line of work of Bayesian inference for Hawkes processes, and derive an inference algorithm by performing inference on an aggregated sum of Gaussian Processes. Approximate Bayesian inference is achieved via data augmentation, and we describe a mean-field variational inference approach to learn the model parameters. To demonstrate the flexibility of the model we apply our methodology on data from different domains and compare it to previously reported results. 相似文献
