Optimization-based meta-learning has been applied in coldstart recommendations, where a good initialization of meta learner is obtained from past experiences and then reused for fast adaptation to new tasks. However, when dealing with various users with diverse preferences, meta-learning with a single prior might fail in cold-start recommendations due to its insufficient capability for adaptation. To address this problem, a multi-prior meta-learning (MPML) approach is proposed in this paper and applied in cold-start recommendations. More concretely, we integrate a novel accuracy-based task clustering scheme with double gradient to learn multiple priors. Experiments demonstrate the effectiveness of MPML.
China Earthquake Parameter Zoning (2016) has increased the seismic fortification intensity in Chengdu from VII to VIII. It is necessary to conduct in-depth discussion on the impact of the seismic performance of the built underground station structure. In this paper, a stratum-structure finite element model is established with a Chengdu subway station as an example. The model boundary adopts viscoelastic boundary, and the ground motion is input in the form of equivalent nodal force. The equivalent linearization method is used to consider the nonlinearity of soil materials. The time-history analysis of seismic fortification intensity of VII and VIII degrees is carried out, respectively. By comparing the calculation results of the two seismic fortification intensity ground motion conditions, it is concluded that the connection between the side wall and the floor is the weakest position of the station structure under the action of the earthquake; the seismic fortification intensity is increased from VII to VIII to the internal force of the structure. It has a relatively large impact, especially the most obvious impact on the bending moment. The results of the verification of the seismic time-history analysis show that the increase of fortification intensity will have a more obvious impact on the structural deformation, and the structural design of the station can meet the safety performance requirements of VII and VIII degrees of seismic fortification. The research has certain reference significance for the seismic safety evaluation of the built underground station structure in Chengdu area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.