检索结果-内蒙古大学图书馆

A hierarchical reinforced sequence operation method for unsupervised text style transfer

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wu, Chen Ren, Xuancheng Luo, Fuli Sun, Xu Department of Foreign Languages and Literatures Tsinghua University MOE Key Laboratory of Computational Linguistics School of EECS Peking University Center for Data Science Beijing Institute of Big Data Research Peking University

Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision. Existing seq2seq methods face three challenges: 1) the transfer is weakly interpretable, 2) generated outputs struggle in content preservation, and 3) the trade-off between content and style is intractable. To address these challenges, we propose a hierarchical reinforced sequence operation method, named Point-Then-Operate (PTO), which consists of a high-level agent that proposes operation positions and a lowlevel agent that alters the sentence. We provide comprehensive training objectives to control the fluency, style, and content of the outputs and a mask-based inference algorithm that allows for multi-step revision based on the single-step trained agents. Experimental results on two text style transfer datasets show that our method significantly outperforms recent methods and effectively addresses the aforementioned challenges. Copyright © 2019, The Authors. All rights reserved.

关键词： Economic and social effects

Facilitating the Electrochemical Oxidation of ZnS through Iodide Catalysis for Aqueous Zinc-Sulfur Batteries

学校读者我要写书评

暂无评论

Angewandte Chemie 2024年第9期136卷

作者： Peng Hei Ya Sai Chang Liu Wenjie Li Jing Wang Xiaoqi Sun Yu Song Xiao-Xia Liu Department of Chemistry Northeastern University 3-11 Wenhua Road Heping district Shenyang 110819 China State Key Laboratory of Metastable Materials Science and Technology Yanshan University Qinhuangdao 066004 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University 3-11 Wenhua Road Heping district Shenyang 110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education 3-11 Wenhua Road Heping district Shenyang 110819 China

Aqueous zinc-sulfur (Zn-S) batteries show great potential for unlocking high energy and safety aqueous batteries. Yet, the sluggish kinetic and poor redox reversibility of the sulfur conversion reaction in aqueous solution challenge the development of Zn-S batteries. Here, we fabricate a high-performance Zn-S battery using highly water-soluble ZnI 2 as an effective catalyst. In situ experimental characterizations and theoretical calculations reveal that the strong interaction between I − and the ZnS nanoparticles (discharge product) leads to the atomic rearrangement of ZnS, weakening the Zn-S bonding, and thus facilitating the electrochemical oxidation reaction of ZnS to S. The aqueous Zn-S battery exhibited a high energy density of 742 Wh kg (sulfur) −1 at the power density of 210.8 W kg (sulfur) −1 and good cycling stability over 550 cycles. Our findings provide new insights about the iodide catalytic effect for cathode conversion reaction in Zn-S batteries, which is conducive to promoting the future development of high-performance aqueous batteries.

关键词： Aqueous Battery Catalytic Effect High Performance I− Additive Mechanism Study

Dark energy and matter interacting scenario to relieve H0 and S8 tensions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Li-Yang Xue, She-Sheng Zhang, Xin Department of Physics College of Sciences Northeastern University Shenyang110819 China Kapteyn Astronomical Institute University of Groningen P.O. Box 800 Groningen9700 AV Netherlands ICRANet Piazzale della Repubblica Pescara10-65122 Italy ICTP-AP University of Chinese Academy of Sciences Beijing China Physics Department Sapienza University of Rome P.le A. Moro 5 Rome00185 Italy INFN Sezione di Perugia Via A. Pascoli PerugiaI-06123 Italy Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China

We consider a new cosmological model (called Λ˜CDM) in which the vacuum energy interacts with matter and radiation, and test this model using the current cosmological observations. Using the CMB+BAO+SN (CBS) dataset to constrain the model, we find that H0 and S8 tensions are relieved to 2.87σ and 2.77σ, respectively. However, in this case, the Λ˜CDM model is not favored by the data, compared with ΛCDM. We find that when the H0 and S8 data are added to the data combination, the situation is significantly improved. In the CBS+H0 case, the model relieves the H0 tension to 0.47σ, and the model is favored over ΛCDM. In the CBS+H0+S8 case, we obtain a synthetically best situation, in which the H0 and S8 tensions are relieved to 0.72σ and 2.11σ, respectively. In this case, the model is most favored by the data. Therefore, this cosmological model can greatly relieve the H0 tension and simultaneously effectively alleviate the S8 tension. Copyright © 2022, The Authors. All rights reserved.

关键词： Electric circuit breakers

Intrablock interleaving for Batched network coding with blockwise adaptive recoding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yin, Hoover H.F. Ng, Ka Hei Zhong, Allen Z. Yeung, Raymond W. Yang, Shenghao Chan, Ian Y.Y. The N-hop Technologies Limited Hong Kong The Institute of Network Coding The Chinese University of Hong Kong Hong Kong The Department of Information Engineering The Chinese University of Hong Kong Hong Kong Limited The Department of Physics The Chinese University of Hong Kong Hong Kong The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China The Department of Economics The Chinese University of Hong Kong Hong Kong

Batched network coding (BNC) is a low-complexity solution to network transmission in multi-hop packet networks with packet loss. BNC encodes the source data into batches of packets. As a network coding scheme, the intermediate nodes perform recoding on the received packets belonging to the same batch instead of just forwarding them. A recoding scheme that may generate more recoded packets for batches of a higher rank is also called adaptive recoding. Meanwhile, in order to combat burst packet loss, the transmission of a block of batches can be interleaved. Stream interleaving studied in literature achieves the maximum separation among any two consecutive packets of a batch, but permutes packets across blocks and hence cannot bound the buffer size and the latency. To resolve the issue of stream interleaver, we design an intrablock interleaver for adaptive recoding that can preserve the advantages of using a block interleaver when the number of recoded packets is the same for all batches. We use potential energy in classical mechanics to measure the performance of an interleaver, and propose an algorithm to optimize the interleaver with this performance measure. Our problem formulation and algorithm for intrablock interleaving are also of independent interest. © 2021, CC BY-NC-ND.

关键词： Network coding

Document hashing with mixture-prior generative models

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Dong, Wei Su, Qinliang Shen, Dinghan Chen, Changyou School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China ECE Department Duke University CSE Department SUNY Buffalo United States

Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes. Generative hashing is often used to generate hashing codes in an unsupervised way. However, existing generative hashing methods only considered the use of simple priors, like Gaussian and Bernoulli priors, which limits these methods to further improve their performance. In this paper, two mixture-prior generative models are proposed, under the objective to produce high-quality hashing codes for documents. Specifically, a Gaussian mixture prior is first imposed onto the variational auto-encoder (VAE), followed by a separate step to cast the continuous latent representation of VAE into binary code. To avoid the performance loss caused by the separate casting, a model using a Bernoulli mixture prior is further developed, in which an endto- end training is admitted by resorting to the straight-through (ST) discrete gradient estimator. Experimental results on several benchmark datasets demonstrate that the proposed methods, especially the one using Bernoulli mixture priors, consistently outperform existing ones by a substantial margin. Copyright © 2019, The Authors. All rights reserved.

关键词： Binary codes

Attention-guided sampling for colorectal cancer analysis with digital pathology

学校读者我要写书评

暂无评论

Journal of Pathology Informatics 2022年 13卷 100110-100110页

作者： Broad, Andrew Wright, Alexander I. de Kamps, Marc Treanor, Darren School of Computing University of Leeds Sir William Henry Bragg Building Woodhouse Lane UK Leeds LS2 9BW United Kingdom Leeds Institute for Data Analytics University of Leeds Level 11 Worsley Building Clarendon Way UK Leeds LS2 9NL United Kingdom Leeds Teaching Hospitals NHS Trust Beckett St Harehills UK Leeds LS9 7TF United Kingdom Division of Pathology and Data Analytics Leeds Institute of Medical Research University of Leeds St James's University Hospital UK Leeds LS9 7TF United Kingdom The Alan Turing Institute 96 Euston Road UK London NW1 2DB United Kingdom University of Leeds UK Leeds LS2 9JT United Kingdom Department of Clinical Pathology Department of Clinical and Experimental Medicine Linköping University Linköping Sweden Center for Medical Image Science and Visualization (CMIV) Linköping University Linköping Sweden

Improvements to patient care through the development of automated image analysis in pathology are restricted by the small image patch size that can be processed by convolutional neural networks (CNNs), when compared to the whole-slide image (WSI). Tile-by-tile processing across the entire WSI is slow and inefficient. While this may improve with future computing power, the technique remains vulnerable to noise from uninformative image areas. We propose a novel attention-inspired algorithm that selects image patches from informative parts of the WSI, first using a sparse randomised grid pattern, then iteratively re-sampling at higher density in regions where a CNN classifies patches as tumour. Subsequent uniform sampling across the enclosing region of interest (ROI) is used to mitigate sampling bias. Benchmarking tests informed the adoption of VGG19 as the main CNN architecture, with 79% classification accuracy. A further CNN was trained to separate false-positive normal epithelium from tumour epithelium, in a novel adaptation of a two-stage model used in brain imaging. These subsystems were combined in a processing pipeline to generate spatial distributions of classified patches from unseen WSIs. The ROI was predicted with a mean F1 (Dice) score of 86.6% over 100 evaluation WSIs. Several algorithms for evaluating tumour–stroma ratio (TSR) within the ROI were compared, giving a lowest root mean square (RMS) error of 11.3% relative to pathologists’ annotations, against 13.5% for an equivalent tile-by-tile pipeline. Our pipeline processed WSIs between 3.3x and 6.3x faster than tile-by-tile processing. We propose our attention-based sampling pipeline as a useful tool for pathology researchers, with the further potential for incorporating additional diagnostic calculations. © 2022 The Authors

关键词： Artificial intelligence Attention Colorectal cancer Region of interest Sampling Tumour–stroma ratio

Diatomic Catalysts for Aqueous Zinc-Iodine Batteries: Mechanistic Insights and Design Strategies

学校读者我要写书评

暂无评论

Angewandte Chemie 2024年第49期136卷

作者： Peng Hei Ya Sai Wenjie Li Jianming Meng Yulai Lin Xiaoqi Sun Jing Wang Yu Song Xiao-Xia Liu Department of Chemistry Northeastern University 3-11 Wenhua Road Heping district Shenyang 110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University 3-11 Wenhua Road Heping district Shenyang 110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University) Ministry of Education 3-11 Wenhua Road Heping district Shenyang 110819 China State Key Laboratory of Metastable Materials Science and Technology Yanshan University Qinhuangdao 066004 China

There has been a growing interest in developing catalysts to enable the reversible iodine conversion reaction for high-performance aqueous zinc-iodine batteries (AZIBs). While diatomic catalysts (DACs) have demonstrated superior performance in various catalytic reactions due to their ability to facilitate synergistic charge interactions, their application in AZIBs remains unexplored. Herein, we present, for the first time, a DAC comprising Mn−Zn dual atoms anchored on a nitrogen-doped carbon matrix (MnZn−NC) for iodine loading, resulting in a high-performance AZIB with a capacity of 224 mAh g −1 at 1 A g −1 and remarkable cycling stability over 320,000 cycles. The electron hopping along the Mn−N−Zn bridge is stimulated via a spin exchange mechanism. This process broadens the Mn 3d xy band width and enhances the metallic character of the catalyst, thus facilitating charge transfer between the catalysts and reaction intermediates. Additionally, the increased electron occupancy within the d-orbital of Zn elevates Zn's d-band center, thereby enhancing chemical interactions between MnZn−NC and I-based species. Furthermore, our mechanism demonstrates potential applicability to other Metal-Zn−NC DACs with spin-polarized atoms. Our work elucidates a clear mechanistic understanding of diatomic catalysts and provides new insights into catalyst design for AZIBs.

关键词： Aqueous zinc-iodine batteries Diatomic catalyst Catalytic mechanism Spin exchange

Multi-Source Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Han, Zhu Zhang, Ce Gao, Lianru Zeng, Zhiqiang Ng, Michael K. Zhang, Bing Chanussot, Jocelyn Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China International Research Center of Big Data for Sustainable Development Goals Beijing100094 China College of Resources and Environment University of Chinese Academy of Sciences Beijing100049 China School of Geographical Sciences University of Bristol BristolBS8 1SS United Kingdom The UK Center of Ecology & Hydrology Library Avenue LancasterLA1 4AP United Kingdom Beijing Institute of Remote Sensing Equipment Beijing100854 China Department of Mathematics Hong Kong Baptist University Hong Kong Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Univ. Grenoble Alpes CNRS Grenoble INP IJK Grenoble38000 France The Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions and reduce hand-crafted cost in the field of remote sensing. However, existing approaches focus on single-source domain generalization to unseen target domains, and are easily confused by large real-world domain shifts due to the limited training information and insufficient diversity modeling capacity. To address this gap, we propose a novel multi-source collaborative domain generalization framework (MS-CDG) based on homogeneity and heterogeneity characteristics of multi-source remote sensing data, which considers data-aware adversarial augmentation and model-aware multi-level diversification simultaneously to enhance cross-scene generalization performance. The data-aware adversarial augmentation adopts an adversary neural network with semantic guide to generate MS samples by adaptively learning realistic channel and distribution changes across domains. In views of cross-domain and intra-domain modeling, the model-aware diversification transforms the shared spatial-channel features of MS data into the class-wise prototype and kernel mixture module, to address domain discrepancies and cluster different classes effectively. Finally, the joint classification of original and augmented MS samples is employed by introducing a distribution consistency alignment to increase model diversity and ensure better domain-invariant representation learning. Extensive experiments on three public MS remote sensing datasets demonstrate the superior performance of the proposed method when benchmarked with the state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guan, Yushuo Liu, Ning Zhao, Pengyu Che, Zhengping Bian, Kaigui Wang, Yanzhi Tang, Jian The School of Computer Science Peking University Beijing100871 China Midea Group Beijing100102 China The School of Computer Science National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing100871 China The Department of Electrical & Computer Engineering Northeastern University BostonMA02115 United States

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Channel pruning is usually applied to reduce the model redundancy while preserving the network structure, such that the pruned network can be easily deployed in practice. However, existing channel pruning methods require hand-crafted rules, which can result in a degraded model performance with respect to the tremendous potential pruning space given large neural networks. In this paper, we introduce Differentiable Annealing Indicator Search (DAIS) that leverages the strength of neural architecture search in the channel pruning and automatically searches for the effective pruned model with given constraints on computation overhead. Specifically, DAIS relaxes the binarized channel indicators to be continuous and then jointly learns both indicators and model parameters via bi-level optimization. To bridge the non-negligible discrepancy between the continuous model and the target binarized model, DAIS proposes an annealing-based procedure to steer the indicator convergence towards binarized states. Moreover, DAIS designs various regularizations based on a priori structural knowledge to control the pruning sparsity and to improve model performance. Experimental results show that DAIS outperforms state-of-the-art pruning methods on CIFAR-10, CIFAR-100, and ImageNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Annealing