检索结果-内蒙古大学图书馆

31st Canadian Conference on Computational Geometry, CCCG 2019

作者： Demaine, Martin L. Hearn, Robert Ku, Jason Uehara, Ryuhei Computer Science and Artificial Intelligence Lab MIT Electrical Engineering and Computer Science Department MIT Japan Advanced Institute of Science and Technology School of Information Science Japan

In this paper, we investigate the problem that asks if there exists a net of a polycube that is exactly a rectangle with slits. For this nontrivial question, we show affirmative solutions. First, we show some concrete examples: (1) no rectangle with slits with fewer than 24 squares can fold to any polycube, (2) a 4 × 7 rectangle with slits can fold to a heptacube (nonmanifold), (3) both of a 3 × 8 rectangle and a 4 × 6 rectangle can fold to a hexacube (nonmanifold), and (4) a 5 × 6 rectangle can fold to a heptacube (manifold). Second, we show a construction of infinite family of polycubes folded from a rectangle with slits. The smallest one given by this construction is a 6 × 20 rectangle with slits that can fold to a polycube of genus 5. This construction gives us a polycube for any positive genus. Moreover, by this construction, we can show that there exists a rectangle with slits that can fold to k different polycubes for any given positive integer k. © CCCG 2019. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DICE: Dynamically Induced Cross Entropy for Robust Learning with Noisy labels 6th

DICE: Dynamically Induced Cross Entropy for Robust Learning ...

引用

6th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2021

作者： Liu, Tianyu State Key Lab on Intelligence Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9789811692468

Image classification has lead to the revolution of artificial intelligence in the past five years. However, image classification algorithms are significantly affected by the inherent variance in sensory input and noise in the labelled data in a real-world situation. Also, the class count of items in the real world is significantly larger than that of the typical experiment setup. How to speedily train/fine-tune a large scale model in giant label space with considerable noise is a recent interest of the machine learning community. This paper proposed a multi-stage training algorithm to fine-tune a pre-trained EfficientNet model on AliProducts large scale product classification dataset, which has a large label space (50030 classes) and severe label noise. Our method can generalize well on such a dataset while keeping the prior knowledge gained in the large-scale pretraining stage. With our novel Dynamically Induced Cross-Entropy(DICE) network loss and several other methods to tackle unbalanced datasets and improve model convergence, the model achieved 76.67% of Top-1 Accuracy and 85.42% of Top-5 accuracy, which are 3.63%/2.9% higher than symmetric cross-entropy and are significantly higher than the usual fine-tuning method with categorical cross-entropy loss(CCE). © 2022, Springer Nature Singapore Pte Ltd.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Voltage island generation in cell based dual-Vdd design

Voltage island generation in cell based dual-Vdd design

引用

作者： Cai, Yici Liu, Bin Zhou, Qiang Hong, Xianlong EDA lab. Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science University of California Los Angeles United States

The voltage island style has been widely accepted as an effective way to design low power high performance chips. This paper proposes an automated voltage island generation flow in standard cell based designs. Two important objectives in voltage island designs are addressed in this flow: 1) reducing power dissipation under given performance constraints;2) reducing implementation overheads, mainly layout overheads caused by cell clustering to form islands. The first objective is handled with timing and power driven netweighting and timing analysis in voltage assignment. For the second objective, we propose layout aware voltage assignment, i.e., voltage assignment during placement. We iteratively perform the following to adjustments: adjustment on voltage assignment to facilitate voltage island generation, and adjustment on cell locations to cluster cells in voltage islands. These iterations lead to a flow featured with tightly integrated voltage assignment and cell placement. Experimental results have demonstrated the advantages of our approach. © 2007 The Institute of Electronics, Information and Communication Engineers.

关键词： Electric power generation

来源：评论

学校读者我要写书评

暂无评论

Secure key-aggregation authorized searchable encryption

引用

science China(Information sciences) 2019年第3期62卷 220-222页

作者： Haijiang WANG Xiaolei DONG Zhenfu CAO Dongmei LI Nanyuan CAO School of Information and Electronic Engineering Zhejiang University of Science and Technology Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai Key Lab for Trustworthy Computing East China Normal University

Dear editor,Selective sharing of encrypted documents with other users makes the cloud storage system more flexible and effective [1]. For safety reasons, data owners use different keys to encrypt different documents. ... 详细信息

关键词： MSK ID length

来源：评论

学校读者我要写书评

暂无评论

Query Augmentation with Brain Signals 24

Query Augmentation with Brain Signals

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ye, Ziyi Zhan, Jingtao Ai, Qingyao Liu, Yiqun De Rijke, Maarten Lioma, Christina Ruotsalo, Tuukka Department of Computer Science and Technology Tsinghua University Quancheng Lab Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Zhongguancun Lab Beijing China University of Amsterdam Amsterdam Netherlands University of Copenhagen Copenhagen Denmark Lut University Lahti Finland

ISBN: (纸本)9798400706868

In the information retrieval scenario, query augmentation is an essential technique to refine semantically imprecise queries to align more closely with users' actual information needs. Traditional methods typically rely on extracting signals from user interactions such as browsing or clicking behaviors to augment the queries, which may not accurately reflect the actual user intent due to inherent noise and the dependency on initial user interactions. To overcome these limitations, we introduce Brain-Aug, a novel approach that decodes semantic information directly from brain signals of users to augment query representation. Brain-Aug builds on three techniques: (i) Structurally, an adapter network is utilized to project brain signals into the embedding space of a language model, allowing query augmentation conditioned on both the users' initial query and their brain signals. (ii) During training, we use a next token prediction task for query augmentation and adopt prompt tuning to efficiently train the brain adapter. (iii)At the inference stage, a ranking-oriented decoding strategy is implemented, enabling Brain-Aug to generate augmentations that improve ranking performance. We evaluate our approach on multiple functional magnetic resonance imaging (fMRI) datasets, demonstrating that Brain-Aug not only produces semantically richer queries but also significantly improves document ranking accuracy, particularly for ambiguous queries. These results validate the effectiveness of Brain-Aug, and reveal the potential of using internal cognitive states to understand and augment text-based queries. Supplementary materials and code are available at https://***/YeZiyi1998/Brain-Query-Augmentation. © 2024 Owner/Author.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dual training and dual prediction for polarity classification

Dual training and dual prediction for polarity classificatio...

引用

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Xia, Rui Wang, Tao Hu, Xuelei Li, Shoushan Zong, Chengqing Department of Computer Science Nanjing University of Science and Technology China NLP Lab. Department of Computer Science Soochow University China National Lab. of Pattern Recognition Institute of Automation CAS China

ISBN: (纸本)9781937284510

Bag-of-words (BOW) is now the most popular way to model text in machine learning based sentiment classification. However, the performance of such approach sometimes remains rather limited due to some fundamental deficiencies of the BOW model. In this paper, we focus on the polarity shift problem, and propose a novel approach, called dual training and dual prediction (DTDP), to address it. The basic idea of DTDP is to first generate artificial samples that are polarity-opposite to the original samples by polarity reversion, and then leverage both the original and opposite samples for (dual) training and (dual) prediction. Experimental results on four datasets demonstrate the effectiveness of the proposed approach for polarity classification. © 2013 Association for Computational Linguistics.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Regularization of Small Sub-Constraint Satisfaction Problems 22nd

The Regularization of Small Sub-Constraint Satisfaction Prob...

引用

22nd International Conference on Applications of Declarative programming and Knowledge Management, INAP 2019, the 33rd Workshop on Logic programming, WLP 2019, and the 27th Workshop on Functional and Constraint Logic programming, WFLP 2019

作者： Löffler, Sven Liu, Ke Hofstedt, Petra Department of Mathematics and Computer Science MINT Programming Languages and Compiler Construction Group Brandenburg University of Technology Cottbus-Senftenberg Konrad-Wachsmann-Allee 5 Cottbus03044 Germany

ISBN: (纸本)9783030467135

This paper describes a new approach on optimization of constraint satisfaction problems (CSPs) by means of substituting sub-CSPs with locally consistent regular membership constraints. The purpose of this approach is to reduce the number of fails in the resolution process, to improve the inferences made during search by the constraint solver by strengthening constraint propagation, and to maintain the level of propagation while reducing the cost of propagating the constraints. Our experimental results show improvements in terms of the resolution speed compared to the original CSPs and a competitiveness to the recent tabulation approach [1, 15]. Besides, our approach can be realized in a preprocessing step, and therefore wouldn’t collide with redundancy constraints or parallel computing if implemented. © 2020, Springer Nature Switzerland AG.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Proposed Biometric Security System Based on Deep Learning and Chaos Algorithms

引用

computers, Materials & Continua 2023年第2期74卷 3515-3537页

作者： Iman Almomani Walid El-Shafai Aala AlKhayer Albandari Alsumayt Sumayh S.Aljameel Khalid Alissa Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Computer Science Department King Abdullah II School of Information TechnologyThe University of Jordan11942Jordan Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Computer Science Department Applied CollegeImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Computer Science Department College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia SAUDI ARAMCO Cybersecurity Chair Networks and Communications DepartmentCollege of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia

Nowadays,there is tremendous growth in biometric authentication and cybersecurity ***,the efficient way of storing and securing personal biometric patterns is mandatory in most governmental and private ***,designing and implementing robust security algorithms for users’biometrics is still a hot research area to be *** work presents a powerful biometric security system(BSS)to protect different biometric modalities such as faces,iris,and *** proposed BSSmodel is based on hybridizing auto-encoder(AE)network and a chaos-based ciphering algorithm to cipher the details of the stored biometric patterns and ensures their *** employed AE network is unsupervised deep learning(DL)structure used in the proposed BSS model to extract main biometric *** obtained features are utilized to generate two random chaos *** first random chaos matrix is used to permute the pixels of biometric *** contrast,the second random matrix is used to further cipher and confuse the resulting permuted biometric pixels using a two-dimensional(2D)chaotic logisticmap(CLM)*** assess the efficiency of the proposed BSS,(1)different standardized color and grayscale images of the examined fingerprint,faces,and iris biometrics were used(2)comprehensive security and recognition evaluation metrics were *** assessment results have proven the authentication and robustness superiority of the proposed BSSmodel compared to other existing *** example,the proposed BSS succeeds in getting a high area under the receiver operating characteristic(AROC)value that reached 99.97%and low rates of 0.00137,0.00148,and 3516 CMC,2023,vol.74,no.20.00157 for equal error rate(EER),false reject rate(FRR),and a false accept rate(FAR),respectively.

关键词： Biometric security deep learning AE network 2D CLM cybersecurity and authentication applications feature extraction unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Find truth in the hands of the few:acquiring specific knowledge with crowdsourcing

引用

Frontiers of computer science 2021年第4期15卷 5-16页

作者： Tao HAN Hailong SUN Yangqiu SONG Yili FANG Xudong LIU SKLSDE Lab School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyClearwater BayHong Kong 999077China School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhou 310018China

Crowdsourcing has been a helpful mechanism to leverage human intelligence to acquire useful ***,when we aggregate the crowd knowledge based on the currently developed voting algorithms,it often results in common knowledge that may not be *** this paper,we consider the problem of collecting specific knowledge via *** the help of using external knowledge base such as WordNet,we incorporate the semantic relations between the alternative answers into a probabilisticmodel to determine which answer is more *** formulate the probabilistic model considering both worker’s ability and task’s difficulty from the basic assumption,and solve it by the expectation-maximization(EM)*** increase algorithm compatibility,we also refine our method into semi-supervised *** results show that our approach is robust with hyper-parameters and achieves better improvement thanmajority voting and other algorithms when more specific answers are expected,especially for sparse data.

关键词： crowdsourcing knowledge acquisition EM algorithm label aggregation

来源：评论

学校读者我要写书评

暂无评论

Unknown Intent Detection Using Multi-Objective Optimization on Deep Learning Classifiers

Unknown Intent Detection Using Multi-Objective Optimization ...

引用

International Conference on Recent Advances in Natural Language Processing: Deep Learning for Natural Language Processing Methods and Applications, RANLP 2021

作者： Prem, Prerna Ahmad, Zishan Ekbal, Asif Sengupta, Shubhashis Jain, Sakshi C. Ramnani, Roshni Department of Computer Science and Engineering Indian Institute of Technology Patna India Accenture Technology Lab Bangalore India

ISBN: (纸本)9789544520724

Modelling and understanding dialogues in a conversation depends on identifying the user intent from the given text. Unknown or new intent detection is a critical task, as in a realistic scenario a user intent may frequently change over time and divert even to an intent previously not encountered. This task of separating the unknown intent samples from known intents one is challenging as the unknown user intent can range from intents similar to the predefined intents to something completely different. Prior research on intent discovery often consider it as a classification task where an unknown intent can belong to a predefined set of known intent classes. In this paper we tackle the problem of detecting a completely unknown intent without any prior hints about the kind of classes belonging to unknown intents. We propose an effective post-processing method using multi-objective optimization to tune an existing neural network based intent classifier and make it capable of detecting unknown intents. We perform experiments using existing state-of-the-art intent classifiers and use our method on top of them for unknown intent detection. Our experiments across different domains and real-world datasets show that our method yields significant improvements compared with the state-of-the-art methods for unknown intent detection. © 2021 Incoma Ltd. All rights reserved.

关键词： Multiobjective optimization

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：