Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs from solving many important computer vision tasks, such as Action Recognition in Videos and Image Captioning. To overcome this problem, we propose a compact and flexible structure, namely Block-Term tensor decomposition, which greatly reduces the parameters of RNNs and improves their training efficiency. Compared with alternative low-rank approximations, such as tensortrain RNN (TT-RNN), our method, Block-Term RNN (BT-RNN), is not only more concise (when using the same rank), but also able to attain a better approximation to the original RNNs with much fewer parameters. On three challenging tasks, including Action Recognition in Videos, Image Captioning and Image Generation, BT-RNN outperforms TT-RNN and the standard RNN in terms of both prediction accuracy and convergence rate. Specifically, BT-LSTM utilizes 17,388 times fewer parameters than the standard LSTM to achieve an accuracy improvement over 15.6% in the Action Recognition task on the UCF11 dataset.
The objective of this paper is to present the development and implementation of a prototype cyberinfrastructure, called SWATShare, for sharing, running and visualizing Soil and Water Assessment Tool (SWAT). SWATShare is developed as a collaborative environment for hydrology research and education using the models published and shared in the system.SWATShare also provides capabilities for model discovery, downloading, running and visualization of model simulations. Some of the functions in SWATShare are supported by providing access to high performance computing resources including the XSEDE and cloud.SWATShare can also be used as an educational tool within a classroom setting for comparing the hydrologic processes under different geographic and climatic settings. The utility of SWATShare for collaborative research and education is demonstrated by using three case studies. Even though this paper focuses on the SWAT model, the system's architecture can be replicated for other models for collaborative research and education.
No abstract
Motivation: By capturing various biochemical interactions, biological pathways provide insight into underlying biological processes. Given high-dimensional microarray or RNA-sequencing data, a critical challenge is how to integrate them with rich information from pathway databases to jointly select relevant pathways and genes for phenotype prediction or disease prognosis. Addressing this challenge can help us deepen biological understanding of phenotypes and diseases from a systems perspective.Results: In this article, we propose a novel sparse Bayesian model for joint network and node selection. This model integrates information from networks (e.g. pathways) and nodes (e.g. genes) by a hybrid of conditional and generative components. For the conditional component, we propose a sparse prior based on graph Laplacian matrices, each of which encodes detailed correlation structures between network nodes. For the generative component, we use a spike and slab prior over network nodes. The integration of these two components, coupled with efficient variational inference, enables the selection of networks as well as correlated network nodes in the selected networks.Simulation results demonstrate improved predictive performance and selection accuracy of our method over alternative methods. Based on three expression datasets for cancer study and the KEGG pathway database, we selected relevant genes and pathways, many of which are supported by biological literature. In addition to pathway analysis, our method is expected to have a wide range of applications in selecting relevant groups of correlated high-dimensional biomarkers.Availability: The code can be downloaded at www.cs.purdue.edu/homes/szhe/software.html.Contact: alanqi@purdue.edu
Kernel support vector machines (SVMs) deliver state-of-the-art results in many real-world nonlinear classification problems, but the computational cost can be quite demanding in order to maintain a large number of support vectors. Linear SVM, on the other hand, is highly scalable to large data but only suited for linearly separable problems. In this paper, we propose a novel approach called low-rank linearized SVM to scale up kernel SVM on limited resources. Our approach transforms a nonlinear SVM to a linear one via an approximate empirical kernel map computed from efficient kernel low-rank decompositions. We theoretically analyze the gap between the solutions of the approximate and optimal rank-k kernel map, which in turn provides guidance on the sampling scheme of the Nyström approximation. Furthermore, we extend it to a semisupervised metric learning scenario in which partially labeled samples can be exploited to further improve the quality of the low-rank embedding. Our approach inherits rich representability of kernel SVM and high efficiency of linear SVM. Experimental results demonstrate that our approach is more robust and achieves a better tradeoff between model representability and scalability against state-of-the-art algorithms for large-scale SVMs.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.