检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Dong, Qingxiu Dong, Li Xu, Ke Zhou, Guangyan Hao, Yaru Sui, Zhifang Wei, Furu Microsoft Research United States School of Computer Science Peking University China State Key Lab of Software Development Environment Beihang University China Department of Mathematics and Statistics Beijing Technology and Business University China

In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous reasoning throughout 97 dialogue turns, concluding "P ≠ NP", which is in alignment with (Xu and Zhou, 2023). The investigation uncovers novel insights within the extensive solution space of LLMs, shedding light on LLM for science. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

ALGNN: Auto-Designed Lightweight Graph Neural Network 18th

ALGNN: Auto-Designed Lightweight Graph Neural Network

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Cai, Rongshen Tao, Qian Tang, Yufei Shi, Min School of Software South China University of Technology Guangzhou China Department of Computer and Electrical Engineering and Computer Science Florida Atlantic University Boca Raton United States Institute for Informatics Washington University School of Medicine in St. Louis St. Louis United States

ISBN: (纸本)9783030891879

Graph neural networks (GNNs) are widely used on graph-structured data, and its research has made substantial progress in recent years. However, given the various number of choices and combinations of components such as aggregator and activation function, designing GNNs for specific tasks is very heavy manual work. Recently, neural architecture search (NAS) was proposed with the aim of automating the GNN design process and generating task-dependent architectures. While existing approaches have achieved competitive performance, they are not well suited to practical application scenarios where the computational budget is limited. In this paper, we propose an auto-designed lightweight graph neural network (ALGNN) method to automatically design lightweight, task-dependent GNN architectures. ALGNN uses multi-objective optimization to optimize the architecture constrained by the computation cost and complexity of the model. We define, for the first time, an evaluation standard for consumption cost with the analysis of the message passing process in GNNs. Experiments on real-world datasets demonstrate that ALGNN can generate a lightweight GNN model that has much fewer parameters and GPU hours, meanwhile has comparable performance with state-of-the-art approaches. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised Modeling Method for Dioxin Emission Prediction Based on Random Forest 5

A Semi-supervised Modeling Method for Dioxin Emission Predic...

引用

5th Asian Conference on Artificial Intelligence technology, ACAIT 2021

作者： Xu, Wen Tang, Jian Xia, Heng Zhang, Jian Yu, Wen Qiao, JunFei Beijing University of Technology Faculty of Information Technology Beijing100124 China Nanjing University of Information Science Technology School of Computer and Software 210044 China CINVESTAV-IPN National Polytechnic Institute Departamento de Control Automatico Mexico City07360 Mexico

ISBN: (纸本)9781665426305

Dioxin (DXN) is a kind of pollutants with cumulative effects in the municipal solid waste incineration (MSWI) process. Its emission concentration is difficult to detect online and in real-time, which restricts the operational optimization of the MSWI process. At the same time, it is difficult to meet actual needs through traditional supervised modeling methods because of the high time and economic cost of directly measuring DXN. Therefore, a DXN emission prediction model based on semi-supervised random forest (SSRF) is established to make full use of the unlabeled data obtained in the actual industrial process. First, the training subsets are acquired through randomly sampling the labeled data. Second, the training subsets are utilized to build multiple random forest (RF) models and pseudo-label the unlabeled data. Finally, the mixed samples composed of pseudo-labeled data and labeled data are used to train an RF model for predicting the DXN emission concentration. The proposed method is verified by the actual DXN dataset. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Semi-markov CRF Model Based on Stacked Neural Bi-LSTM for Sequence Labeling 3

Semi-markov CRF Model Based on Stacked Neural Bi-LSTM for Se...

引用

3rd IEEE International Conference of Safe Production and Informatization, IICSPI 2020

作者： Liu, Yupeng Li, Guodong Zhang, Xiaochen School of Software Harbin University of Science and Technology Harbin China School of Computer Science and Technology Harbin University of Science and Technology Harbin China School of Materials Chemical and Engineering Heilongjiang Institute of Technology Harbin China

ISBN: (纸本)9781728177380

In this paper, we present a model for sequence labeling. Based on word vector representations of neural network model algorithms and artificial features of statistical machine learning, a stack Bi-LSTM and new semi-Markov conditional random field frameworks are proposed. On the one hand, we present stack Bi-LSTM to achieve segmentation and chunking task on both word-level and character-level. On the other hand, we use traditional CRF and NSCRF to make some restrictions on the labeling entities to improve the accuracy of labels and then use them to decode the unknown sequence. We test the trained model in the CoNLL2000 and CoNLL2003 datasets. © 2020 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution

Feature Aggregating Network with Inter-Frame Interaction for...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Adaptation for Mobile 360-Degree Video Streaming and Enhancement

引用

IEEE Transactions on Mobile Computing 2025年

作者： Guo, Haotian Wang, Feng Zhang, Wei Zhu, Yifei Cui, Laizhong Liu, Jiangchuan Yu, F. Richard Zhang, Lei Shenzhen University College of Computer Science and Software Engineering Guangdong Shenzhen518060 China The University of Mississippi Department of Computer and Information Science MS38677 United States ByteDance Guangdong Shenzhen518060 China University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai200240 China School of Computing Science Simon Fraser University BurnabyBCV5A 1S6 Canada Carleton University School of Information Technology OttawaONK1S 5B6 Canada

Tile-based streaming and super resolution (SR) are two representative technologies adopted to improve bandwidth efficiency of 360° video streaming. The former allows selective downloading of contents in the user viewport by splitting the video into multiple independently decodable tiles. The latter leverages client-side computation to enhance the received video to higher quality using advanced neural network models. In this work, we propose a Collaborated Streaming and Enhancement (CSE) adaptation framework for mobile 360° videos, which integrates super resolution with tile-based streaming to optimize the user experience with dynamic bandwidth and limited computing capability. To effectively enhance the tile-based video streaming through SR, we propose to adaptively group the tiles for quality enhancement adapting to the content similarity. We also identify and address several key design issues to integrate SR into tile-based video streaming including unified video quality assessment, computational complexity model for super resolution, and buffer analysis considering the interplay between transmission and enhancement. We further formulate the quality-of-experience (QoE) maximization problem for mobile 360° video streaming and propose a rate adaptation algorithm to make the best decisions for download and for enhancement based on the Lyapunov optimization theory. Extensive evaluation results validate the superiority of our proposed approach, which demonstrates stable performance with considerable QoE improvement, while enabling a trade-off between playback smoothness and video quality. © 2002-2012 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Region-wise matching for image inpainting based on adaptive weighted low-rank decomposition

arXiv

引用

arXiv 2023年

作者： Liao, Shenghai Liu, Xuya Han, Ruyi Fu, Shujun Zhou, Yuanfeng Li, Yuliang The School of Mathematics Shandong University Jinan250100 China The School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China The School of Software Shandong University Jinan250101 China The Department of Intervention Medicine The Second Hospital of Shandong University Jinan250033 China

Digital image inpainting is an interpolation problem, inferring the content in the missing (unknown) region to agree with the known region data such that the interpolated result fulfills some prior knowledge. Low-rank and nonlocal self-similarity are two important priors for image inpainting. Based on the nonlocal self-similarity assumption, an image is divided into overlapped square target patches (submatrices) and the similar patches of any target patch are reshaped as vectors and stacked into a patch matrix. Such a patch matrix usually enjoys a property of low rank or approximately low rank, and its missing entries are recoveried by low-rank matrix approximation (LRMA) algorithms. Traditionally, n nearest neighbor similar patches are searched within a local window centered at a target patch. However, for an image with missing lines, the generated patch matrix is prone to having entirely-missing rows such that the downstream low-rank model fails to reconstruct it well. To address this problem, we propose a region-wise matching (RwM) algorithm by dividing the neighborhood of a target patch into multiple subregions and then search the most similar one within each subregion. A non-convex weighted low-rank decomposition (NC-WLRD) model for LRMA is also proposed to reconstruct all degraded patch matrices grouped by the proposed RwM algorithm. We solve the proposed NC-WLRD model by the alternating direction method of multipliers (ADMM) and analyze the convergence in detail. Numerous experiments on line inpainting (entire-row/column missing) demonstrate the superiority of our method over other competitive inpainting algorithms. Unlike other low-rank-based matrix completion methods and inpainting algorithms, the proposed model NC-WLRD is also effective for removing random-valued impulse noise and structural noise (stripes). Extension to the restoration of remote sensing images demonstrate that the proposed model has competitive performance for destriping (stripe noise rem

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting Exploiting Global Prior Refined Weighted Low-Rank Representation

SSRN

引用

SSRN 2023年

作者： Liao, Shenghai Liu, Xuya Han, Ruyi Fu, Shujun Zhou, Yuanfeng Li, Yuliang School of Mathematics Shandong University Jinan250100 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China School of Software Shandong University Jinan250101 China Department of Intervention Medicine The Second Hospital of Shandong University Jinan250033 China

Low-rank and nonlocal self-similarity are important priors for image restoration. Based on nonlocal self-similarity assumption, similar patches are grouped into a matrix that is of low-rank or approximately low-rank. Traditional algorithms model low-rank prior of local group matrices (intra-group) and ignore the global inter-group relationship, which will result in suboptimal performance without considering global consistency. Due to overlapping of patches, groups are dependent, however, conventional methods process each group independently. To make full use of the intrinsic relationship among groups, we consider all groups simultaneously and propose a global prior refined weighted low-rank representation model for image inpainting. The local-groups and the aggregation of all groups are taken into account in the proposed model. By introducing auxiliary variable, we decouple the local-global model and optimize iteratively using the alternating direction method of multipliers. The proposed global refinement model significantly improves the performance of local low-rank model. A new strategy for grouping similar patches is also proposed by dividing the neighborhood of a target patch into multiple subregions and searching for a given number of similar patches within each subregion. The proposed method is applied to various tasks (line inpainting, destriping, and depth map completion) and obtains promising performance. © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Band-Gap Engineering and Optoelectronic Properties of 2d Wsi 2 N 4 Nanosheets: A First Principle Calculations

SSRN

引用

SSRN 2022年

作者： Chen, Tong Liu, Guogang Xu, Zhonghui Xiao, Xianbo School of software engineering Jiangxi University of Science and Technology Nanchang330013 China School of Energy and Mechanical Engineering Energy materials computing center Jiangxi University of Science and Technology Nanchang330013 China School of Computer Science Jiangxi University of Chinese Medicine Nanchang330004 China

The successful growth of centimeter-scale monolayer films of MoSi$_{2}$N$_{4}$ and WSi$_{2}$N$_{4}$ has attracted great interest (science 369, 670, 2020). Here, we systematically investigate the effects of biaxial and uniaxial strain on the electronic structures of WSi$_{2}$N$_{4}$ nanosheets with different layers of monolayer(ML), bilayer(BL) and trilayer(TL), respectively, by using first-principles calculations. In addition, combined with the non-equilibrium Green's function methods, the photoelectronic response of WSi$_{2}$N$_{4}$ ML is also explored. The results indicate that: 1) The biaxial and uniaxial strain can flexibly increase or decrease the band gap of WSi$_{2}$N$_{4}$ nanosheets. Particularly, tensile strain realizes the transition of WSi$_{2}$N$_{4}$ nanosheets from semiconductor to metal. 2) The tensile strain effectively improves the optical properties of WSi$_{2}$N$_{4}$ nanosheets in the visible light region, and the red/blue shift of the absorption peaks are observed in the optical spectrum by tensile/compressive strain. 3) The pin-junction photodiode of WSi$_{2}$N$_{4}$ ML generates sizable photocurrents under illumination, showing a strong photoelectronic response to purple light. Furthermore, the biaxial tensile strain significantly enhances the photoelectric performance of the WSi$_{2}$N$_{4}$ photodiode and effectively modulates its detection range in the visible region. Hence, our findings suggest that WSi$_{2}$N$_{4}$ nanosheets are a promising multifunctional material for nanoelectronic and optoelectronic applications. © 2022, The Authors. All rights reserved.

关键词： Monolayers

来源：评论

学校读者我要写书评

暂无评论

GRAPH ATTENTION-BASED DEEP NEURAL NETWORK FOR 3D POINT CLOUD PROCESSING

GRAPH ATTENTION-BASED DEEP NEURAL NETWORK FOR 3D POINT CLOUD...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Li, Xun Xue, Feng Chen, Chao Yuan, Xiaohui Lu, Qiang Ministry of Education Hefei China School of Computer Science and Information Hefei University of Technology Hefei China Hefei China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei China School of Software Hefei University of Technology Hefei China Department of Science and Engineering University of North Texas DentonTX United States

ISBN: (纸本)9781665438643

Due to the increasing popularity of 3D sensors, it has become easier and easier to obtain point cloud data. In many fields such as autonomous driving, how to fully extract the features of point cloud to better understand and perceive 3D scenes requires further research. Therefore, this paper proposes a novel end-to-end deep learning network for the features of disorder and irregularity of 3D point cloud data. Our network uses an encoder-decoder network architecture, and a three-layer structure is used in both stages. Each encoder layer consists of graph attention convolution and graph attention pooling. Graph attention convolution reflects the spatial distribution relationship in the neighborhood area. And graph attention pooling merges the spatial distribution information in the neighborhood into the feature of the sampling point. The experimental results show that our method achieves the best results in shape classification and has competitive performance in other tasks. © 2021 IEEE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：