检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Mingdong Wu Fangwei Zhong Yulong Xia Hao Dong Center on Frontiers of Computing Studies School of Computer Science Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) School of Intelligence Science and Technology Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) Center on Frontiers of Computing Studies School of Computer Science Peking University Center on Frontiers of Computing Studies School of Computer Science Peking University and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Object Rearrangement is to move objects from an initial state to a goal state. Here, we focus on a more practical setting in object rearrangement, i.e., rearranging objects from shuffled layouts to a normative target distribution without explicit goal specification. However, it remains challenging for AI agents, as it is hard to describe the target distribution (goal specification) for reward engineering or collect expert trajectories as demonstrations. Hence, it is infeasible to directly employ reinforcement learning or imitation learning algorithms to address the task. This paper aims to search for a policy only with a set of examples from a target distribution instead of a handcrafted reward function. We employ the score-matching objective to train a Target Gradient Field (TarGF), indicating a direction on each object to increase the likelihood of the target distribution. For object rearrangement, the TarGF can be used in two ways: 1) For model-based planning, we can cast the target gradient into a reference control and output actions with a distributed path planner; 2) For model-free reinforcement learning, the TarGF is not only used for estimating the likelihood-change as a reward but also provides suggested actions in residual policy learning. Experimental results in ball rearrangement and room rearrangement demonstrate that our method significantly outperforms the state-of-the-art methods in the quality of the terminal state, the efficiency of the control process, and scalability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explainable Human-centered Traits from Head Motion and Facial Expression Dynamics

arXiv

引用

arXiv 2023年

作者： Madan, Surbhi Gahalawat, Monika Guha, Tanaya Goecke, Roland Subramanian, Ramanathan Department of Computer Science Indian Institute of Technology Ropar India The Human-Centred Technology Research Centre Faculty of Science and Technology University of Canberra ACT Australia The School of Computing Science University of Glasgow United Kingdom

We explore the efficacy of multimodal behavioral cues for explainable prediction of personality and interview-specific traits. We utilize elementary head-motion units named kinemes, atomic facial movements termed action units and speech features to estimate these human-centered traits. Empirical results confirm that kinemes and action units enable discovery of multiple trait-specific behaviors while also enabling explainability in support of the predictions. For fusing cues, we explore decision and feature-level fusion, and an additive attention-based fusion strategy which quantifies the relative importance of the three modalities for trait prediction. Examining various long-short term memory (LSTM) architectures for classification and regression on the MIT Interview and First Impressions Candidate Screening (FICS) datasets, we note that: (1) Multimodal approaches outperform unimodal counterparts;(2) Efficient trait predictions and plausible explanations are achieved with both unimodal and multimodal approaches, and (3) Following the thin-slice approach, effective trait prediction is achieved even from two-second behavioral snippets. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Faster Exponential-Time Approximation Algorithms Using Approximate Monotone Local Search 30

Faster Exponential-Time Approximation Algorithms Using Appro...

引用

30th Annual European Symposium on Algorithms, ESA 2022

作者： Esmer, Bariş Can Kulik, Ariel Marx, Dániel Neuen, Daniel Sharma, Roohani CISPA Helmholtz Center for Information Security Saarbrücken Germany Saarbrücken Graduate School of Computer Science Saarland Informatics Campus Germany School of Computing Science Simon Fraser University Burnaby Canada Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken Germany

ISBN: (纸本)9783959772471

We generalize the monotone local search approach of Fomin, Gaspers, Lokshtanov and Saurabh [*** 2019], by establishing a connection between parameterized approximation and exponentialtime approximation algorithms for monotone subset minimization problems. In a monotone subset minimization problem the input implicitly describes a non-empty set family over a universe of size n which is closed under taking supersets. The task is to find a minimum cardinality set in this family. Broadly speaking, we use approximate monotone local search to show that a parameterized α-approximation algorithm that runs in ck nO(1) time, where k is the solution size, can be used to derive an α-approximation randomized algorithm that runs in dn nO(1) time, where d is the unique value in ( 1, 1 + c-1 α ) such that D (1 α d-1 c-1 ) = ln c α and D (ab) is the Kullback-Leibler divergence. This running time matches that of Fomin et al. for α = 1, and is strictly better when α > 1, for any c > 1. Furthermore, we also show that this result can be derandomized at the expense of a sub-exponential multiplicative factor in the running time. We use an approximate variant of the exhaustive search as a benchmark for our algorithm. We show that the classic 2n nO(1) exhaustive search can be adapted to an α-approximate exhaustive search that runs in time (1 + exp ( -α H(1 α ))n nO(1), where H is the entropy function. Furthermore, we provide a lower bound stating that the running time of this α-approximate exhaustive search is the best achievable running time in an oracle model. When compared to approximate exhaustive search, and to other techniques, the running times obtained by approximate monotone local search are strictly better for any α ≥ 1, c > 1. We demonstrate the potential of approximate monotone local search by deriving new and faster exponential approximation algorithms for Vertex Cover, 3-Hitting Set, Directed Feedback Vertex Set, Directed Subset Feedback Vertex Set, Directed Odd Cycle Transve

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Training for stable explanation for free 24

Training for stable explanation for free

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chao Chen Chenghua Guo Rufeng Chen Guixiang Ma Ming Zeng Xiangwen Liao Xi Zhang Sihong Xie School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) China Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications China Artificial Intelligence Thrust The Hong Kong University of Science and Technology (Guangzhou) China Intel Carnegie Mellon University College of Computer and Data Science Fuzhou University China

ISBN: (纸本)9798331314385

To foster trust in machine learning models, explanations must be faithful and stable for consistent insights. Existing relevant works rely on the ℓp distance for stability assessment, which diverges from human perception. Besides, existing adversarial training (AT) associated with intensive computations may lead to an arms race. To address these challenges, we introduce a novel metric to assess the stability of top-k salient features. We introduce R2ET which trains for stable explanation by efficient and effective regularizer, and analyze R2ET by multi-objective optimization to prove numerical and statistical stability of explanations. Moreover, theoretical connections between R2ET and certified robustness justify R2ET's stability in all attacks. Extensive experiments across various data modalities and model architectures show that R2ET achieves superior stability against stealthy attacks, and generalizes effectively across different explanation methods. The code can be found at https://***/ccha005/R2ET.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Hidden Patterns in Cancer Genome using Deep Learning

Classification of Hidden Patterns in Cancer Genome using Dee...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Balamurugan K S Sundara Rajulu Navaneethakrishnan Senduru Srinivasulu Kumutha D Surendran R Kalyani G Department of Electronics and Communication Engineering Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of Computer Science and Engineering Dhanalakshmi Srinivasan University Trichy Samayapuram Campus Tiruchirappalli India Department of Computer Science and Engineering School of Computing Sathyabama Institute of science and Technology Chennai India Department of Electronics and Communication Engg. Jeppiaar Institute of Technology Sriperumudur Tamilnadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India RuralCare Innovators LLP Madurai Tamil Nadu India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

The complex structures in cancer genomes are obtained through the revolution of high-throughput technology. The major challenge involves the interpretation of complex sceneries of genomic alterations with the impact of diagnosis and prognosis. The proposed system includes deep-learning techniques that provide optimum solutions for evaluating hidden patterns of the cancer genome. They help to extract important information such as mutation and detection of therapeutic targets. The proposed system involves the aid of a Convolutional Neural Network, Recurrent Neural Network with Long Short Term Memory networks. They help in obtaining intricate genomic data. This is achieved through the spatial relationship and sequential dependencies within the genetic elements. The large-scale genomic datasets are trained which helps to learn the differentiation between the driver and passenger mutations. The genetic alterations provide information regarding the cancer progression. The deep learning model helps in the identification of desperate mutations with exclusive patterns that contribute to tumor development. The important aspect involves the prediction of prognosis. This includes the model to train and learn from the cumulative knowledge of patients in accordance with the genomic profiles. An accurate prognosis and personalized treatments are obtained by analyzing certain parameters such as gene expression, gene mutation and clinical data structures. These optimization techniques help in the identification of complex relationships in the identification of therapeutical compounds.

关键词： Deep learning Accuracy Recurrent neural networks Genomics Prediction algorithms Bioinformatics Prognostics and health management Optimization Cancer Tumors

来源：评论

学校读者我要写书评

暂无评论

Regularized artificial neural network based patent value interval prediction model

Regularized artificial neural network based patent value int...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Weidong Liu Kaiyang Xiao Jiamin Zhang Bo Li Institute of Scientific and Technical Information of China China College of Computer Science Inner Mongolia University China Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Hohhot China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

With the increasing competition in intellectual property rights, patent value prediction has become a hot research issue in the field of intellectual property rights. Most of the current research on patent value either predicts some structural indicators (e.g., citations) or the intrinsic value of patents, but there is relatively little work on predicting the actual value of patents. Patent value prediction faces the following challenges, including: (1)data: the amount of actual transaction data of patents is small and difficult to collect, so the amount of training data and test data can be used is small; (2)features: how to extract the valuation features of the patent, especially technical features from unstructured patent texts; (3)model and validation: how to build a model for predicting patent prices and how to verify the accuracy of our experimental results. To solve these problems, we propose a regularized artificial neural network based patent value interval prediction model: (1) in terms of data, we extract the value data of patents from the official websites of several universities in China, the oceantomo patent trading platform in the United States, and the Patsnap platform, which come with information such as the actual transaction price or the bidding and asking price. (2) in terms of features, we extract the unstructured textual features of patent portfolios, technical features, and structured features of fifteen patents as the valuation features of patents; (3) in terms of model and validation, we use regularized artificial neural networks to give prediction intervals and prediction uncertainty, and validate the model with a measure of numerical intervals. We compare the model with the baseline model and the results show that our model achieves good results.

关键词： Patents Uncertainty Artificial neural networks Intellectual property Predictive models Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Neural Network Based Preselection for Expensive Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Li, Bingdong Yang, Yanting Hong, Wenjing Yang, Peng Zhou, Aimin Shanghai Institute of AI for Education the School of Computer Science and Technology and the Shanghai Frontiers Science Center of Molecule Intelligent Syntheses East China Normal University Shanghai China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural Network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Secured and Optimized Broadcast Authentication Scheme for the Internet of Medical Things

A Secured and Optimized Broadcast Authentication Scheme for ...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Syed Waleed Riaz Fazlullah Khan Insaf Ullah Bandar Alshawi Ryan Alturki Mohammad Wedyan Computer Science Department Abdul Wali Khan University Mardan KPK Pakistan Faculty of Science and Engineering School of Computer Science University of Nottingham Ningbo China Ningbo Zhejiang China Institute for Analytics and Data Science University of Essex Colchester UK Department of Computer and Network Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia Department of Computer Sciences Faculty of Information Technology and Computer Sciences Yarmouk University (YU) Irbid Jordan

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

This Internet of Medical Things (IoMT), facilitates the medical stop regarding real-time monitoring of patients, medical emergency management, remote surgery, patient information management, medical equipment, drug monitoring, etc. However, IoMT devices communicate with each other in an open environment that makes them vulnerable to a wide range of malicious threats from malicious entities. To protect the devices and their associated data, we designed a broadcast authentication scheme for IoMT devices using identity-based public key cryptography that exploits the lightweight features of the Hyper-Elliptic Curve (HEC). We then performed the security analysis based on the Random Oracle Model (ROM), in which we have proved that the proposed scheme is unforgeable under the hardiness of the hyperelliptic curve discrete logarithm problem. The proposed scheme is analyzed in terms of computational and communication overhead and the experimental results justify the superiority of the proposed work in comparison to the existing schemes.

关键词： Performance evaluation Computational modeling Authentication Surgery Internet of Medical Things Public key cryptography Real-time systems Information management Monitoring Read only memory

来源：评论

学校读者我要写书评

暂无评论

Ethereum Phishing Detection Using Hyperbolic Neural Networks and Temporal Information

Ethereum Phishing Detection Using Hyperbolic Neural Networks...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Rong Xu Jun Zhang Xiaoyue Zhu Zhaoxiong Song Zhi Yu College of Computer Science Inner Mongolia University Hohhot China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

In recent years, the frequent occurrence of phishing scams on Ethereum has posed serious threats to transaction security and the financial safety of users. This paper proposes an Ethereum phishing scam detection method based on Hyperbolic Neural Networks (HGNNs) and temporal information. The method maps the Ethereum transaction network to hyperbolic space for structural feature extraction, effectively capturing hierarchical structures and complex relationships within the graph, thereby improving the accuracy of phishing scam detection. The model includes a structural feature extraction module and a temporal feature extraction module. It uses HGNN and self-attention mechanism to extract the structural features of the transaction graph, and uses a multi-head attention mechanism to capture the dynamic evolution pattern of the graph. Experimental validation on real Ethereum datasets demonstrates that the proposed model outperforms benchmark models, showcasing its effectiveness.

关键词： Attention mechanisms Phishing Neural networks Benchmark testing Feature extraction Real-time systems Blockchains Safety Security Tuning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Underwater Object Detection Using Deep Neural networks

Enhanced Underwater Object Detection Using Deep Neural netwo...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： I. R. Oviya Shaik Atheeq Rasool Balu Bhasuran Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Bakar Computational Health Sciences Institute (BCHSI) University of California San Francisco (UCSF) California United States

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The identification of marine animals has become a significant area of data processing and analysis due to the growing volume of underwater visual data and deep sea exploration. The imperative nature of safeguarding the environment underscores the significance of this undertaking; nonetheless, challenges persist due to factors such as intricate underwater scenery, subpar image and video clarity, and the diverse range of motions shown by marine organisms. To solve these challenges, this study used deep learning algorithms to recognize certain marine species and indicate their presence in submitted photos and videos using bounding boxes. The primary objective is to provide practical techniques for identifying marine species, so offering essential support for more research in this field. The study made considerable advancements in detection speed and mean average precision (mAP) for marine species identification by using the key deep learning frameworks, YOLOv3, YOLOv8, and Faster-RCNN. This study project not only resolves the present issues with marine animal detection, but it also lays the foundation for future studies aimed at understanding and safeguarding the delicate underwater ecosystem.

关键词： Deep learning YOLO Visualization Ecosystems Artificial neural networks Data processing Organisms Object recognition Marine animals Motion control

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：