29 July 2014 in Engineering Computations
Purpose – The performance measure approach (PMA) is widely adopted for reliability analysis and reliability-based design optimization because of its robustness and efficiency compared to reliability index approach. However, it has been reported that PMA involves repeat evaluations of probabilistic constraints therefore it is prohibitively expensive for many large-scale applications. In order to overcome these disadvantages, the purpose of this paper is to propose an efficient PMA-based reliability analysis technique using radial basis function (RBF). Design/methodology/approach – The RBF is adopted to approximate the implicit limit state functions in combination with latin hypercube sampling (LHS) strategy. The advanced mean value method is applied to obtain the most probable point (MPP) with the prescribed target reliability and corresponding probabilistic performance measure to improve analysis accuracy. A sequential framework is proposed to relocate the sampling center to the obtained MPP and reconstru...
8 March 2019 in IEEE Transactions on Circuits and Systems II: Express Briefs
29 December 2022 in IEEE Transactions on Neural Networks and Learning Systems
Graph reservoir computing (GraphRC) gains increasing attention by virtue of its high training efficiency. However, since GraphRC is developed without knowledge of its internal mechanism, it cannot be fully trusted to deploy in practice. Although there are some existing approaches that can be extended to interpret GraphRC, the specific role played by each neuron (i.e., reservoir node) of GraphRC is far less explored. To address this issue, the latent short-term memory property of each reservoir node of GraphRC is qualitatively characterized to unravel its role in predicting the graph signal, thereby enabling an interpretable GraphRC. Specifically, we first deduce the equivalence between the GraphRC and conventional reservoir computing (RC). Then, the underlying memory properties of the GraphRC and its reservoir nodes can be characterized in theory by the multisource reachability among the reservoir nodes in the transformed RC. Moreover, the distinct temporal patterns hidden in reservoir nodes are identified, and then, an attention mechanism based on the identified temporal patterns is deployed in the GraphRC to improve its performance. In addition, the effectiveness of the interpretability for GraphRC and improved GraphRC is verified on the Lorenz-96 spatiotemporal dynamical system. The experimental results of the Lorenz-96 spatiotemporal chaotic system and three real-world traffic datasets demonstrate that the improved GraphRC is superior to original GraphRC and can achieve prediction performance comparable to the state-of-the-art baseline models, but with much less training cost.
1 April 2022 in Chaos: An Interdisciplinary Journal of Nonlinear Science
While reservoir computing (RC) has demonstrated astonishing performance in many practical scenarios, the understanding of its capability for generalization on previously unseen data is limited. To address this issue, we propose a novel generalization bound for RC based on the empirical Rademacher complexity under the probably approximately correct learning framework. Note that the generalization bound for the RC is derived in terms of the model hyperparameters. For this reason, it can explore the dependencies of the generalization bound for RC on its hyperparameters. Compared with the existing generalization bound, our generalization bound for RC is tighter, which is verified by numerical experiments. Furthermore, we study the generalization bound for the RC corresponding to different reservoir graphs, including directed acyclic graph (DAG) and Erdős–R nyi undirected random graph (ER graph). Specifically, the generalization bound for the RC whose reservoir graph is designated as a DAG can be refined by leveraging the structural property (i.e., the longest path length) of the DAG. Finally, both theoretical and experimental findings confirm that the generalization bound for the RC of a DAG is lower and less sensitive to the model hyperparameters than that for the RC of an ER graph.
30 April 2025 in Physica A: Statistical Mechanics and its Applications