检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Ma, Changyi Yu, Runsheng Zhang, Youzhi Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation CAS Hong Kong Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798400701719

The similarity matrix is at the core of similarity search problems. However, incomplete observations are ubiquitous in real scenarios leading to a less accurate similarity matrix. To alleviate this problem, in this paper, based on the key insight that the similarity matrix enjoys both the symmetric and positive semi-definiteness (PSD) properties, we propose a novel similarity matrix calibration method, which is scalable, effective, and sound. Specifically, we establish the PSD property as a constraint for the similarity matrix calibration problem and propose a novel similarity matrix calibration method to estimate the similarity matrix, which approximates the unknown complete ground-truth similarity matrix. To enable a fast optimization process, we further develop a general approximated algorithm that bypasses the computation of singular values. Theoretical analysis ensures stable calibration performance and convergence speed. Extensive experiments of similarity matrix calibration on real-world datasets demonstrate that our proposed method outperforms baseline methods in terms of both accuracy and speed. © 2024 ACM.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction 41

Self-Consistency Training for Density-Functional-Theory Hami...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, He Liu, Chang Wang, Zun Wei, Xinran Liu, Siyuan Zheng, Nanning Shao, Bin Liu, Tie-Yan National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Microsoft Research AI for Science United States

Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science ***, its applicability is limited by insufficient labeled data for *** this work, we highlight that Hamiltonian prediction possesses a self-consistency principle, based on which we propose self-consistency training, an exact training method that does not require labeled *** distinguishes the task from predicting other molecular properties by the following benefits: (1) it enables the model to be trained on a large amount of unlabeled data, hence addresses the data scarcity challenge and enhances generalization;(2) it is more efficient than running DFT to generate labels for supervised training, since it amortizes DFT calculation over a set of *** empirically demonstrate the better generalization in data-scarce and out-of-distribution scenarios, and the better efficiency over DFT *** benefits push forward the applicability of Hamiltonian prediction to an ever-larger scale. Copyright 2024 by the author(s)

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Can LLMs Learn From Mistakes? An Empirical Study on Reasoning Tasks

Can LLMs Learn From Mistakes? An Empirical Study on Reasonin...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： An, Shengnan Ma, Zexiong Cai, Siqi Lin, Zeqi Zheng, Nanning Lou, Jian-Guang Chen, Weizhu National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Microsoft United States Peking University China

ISBN: (纸本)9798891761681

Towards enhancing the chain-of-thought (CoT) reasoning of large language models (LLMs), much existing work has revealed the effectiveness of straightforward learning on annotated/generated CoT paths. However, there is less evidence yet that reasoning capabilities can be enhanced through a reverse learning process, i.e., learning from potential mistakes in reasoning. To investigate whether LLMs can learn from mistakes, we construct mistake-correction datasets, using GPT-4 to identify and correct the mistakes in inaccurate CoTs. With these mistake-correction datasets, we fine-tune open-source LLMs and arrive at the following conclusions. (1) LLMs can indeed learn from mistakes to enhance their CoT reasoning performances. (2) Compared to CoT data, the mistake-correction data provides additional knowledge on the explanations and reasons for the potential mistakes in CoTs, which consistently contributes to the effectiveness of learning from mistakes. (3) Evolution techniques, especially the correction-centric evolution we introduced, can further enhance the effectiveness of learning from mistakes. © 2024 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Predictive Model for Morphogenesis of a Robot Sequence Mimicking Protein Folding 14

A Predictive Model for Morphogenesis of a Robot Sequence Mim...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Ni, Zihao Han, Zhi Wang, Shixian Gu, Yuping Yang, Yongliang School of Artificial Intelligence Shenyang University of Technology Liaoning Shenyang110023 China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China

ISBN: (纸本)9798331506056

The swarm phenomena observed in nature have inspired many control algorithms for diverse robot swarm systems. However, most of these endeavors are qualitative simulations aimed at understanding the mechanisms underlying biological swarm behavior. Reliably predicting morphologies of robot swarms from their features remains a formidable challenge. In molecular biology, the 3D structure of a protein molecule, which is a main factor of its functions, is mainly determined by its sequence of amino acids. Inspired by this, our lab developed RoboFold, a robot swarm platform for developing protein-folding-inspired methods controlling the morphologies of robot swarms. Using the data collected from this platform, we proposed a deep learning approach to predict the morphologies of swarm robotics based on their initial sequences. The goal of this research is predicting the initial sequence of robots forming the desired morphology. Preliminary results presented here demonstrated the efficacy of this method and underscore the feasibility of applying protein-folding-inspired methods to program robot swarms. © 2024 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Interactive Multi-Trajectory SLAM for Large-Scale Mapping

Interactive Multi-Trajectory SLAM for Large-Scale Mapping

引用

Chinese Automation Congress (CAC)

作者： Huabiao Feng Liang Zhang Nanning Zheng Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Simultaneous localization and mapping (SLAM) has shown significant success in constructing environmental map. However, as the scale of the environment expands, the accuracy and global consistency of these maps tend to decrease. In response to this challenge, we introduce an interactive multi-trajectory SLAM framework designed for large-scale mapping, with the aim of enhancing both the quality and scale of the generated maps. This framework optimizes a pose graph comprising initial constraints generated by an automatic SLAM process, supplemented by additional map merging and correction constraints created by users via a graphical user interface (GUI). We propose a human-assisted inter-trajectory loop closing technique for manually adding map merging constraints. Evaluation results confirm the efficacy of our proposed framework in achieving a large-scale, consistent environmental map with minimal human effort. Furthermore, it demonstrates robustness for large-scale incremental mapping.

关键词： Simultaneous localization and mapping Accuracy Three-dimensional displays Automation Merging Robustness Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

OCDE: Adaptive Differential Evolution Algorithm in Distributed Intelligent Systems

OCDE: Adaptive Differential Evolution Algorithm in Distribut...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Minghao Wang Shaoyi Du Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798331506896

ISBN: (纸本)9798331506902

In autonomous driving, the optimization theory and algorithms for distributed intelligent systems are essential for enhancing vehicle decision-making capabilities, path planning, and environmental perception. Evolutionary algorithms, as a global optimization method inspired by biological evolution, is widely used in these scenarios. Unfortunately, the performance of evolutionary algorithms relies on the properties of the solution space, the optimization strategy, and parameter settings, and their efficiency also requires more rigorous evaluation. This study focuses on differential evolution algorithm, examining the properties of the solution space for optimization problems, the preferences of strategies and parameters in different optimization scenarios, and setting new standards for efficiency evaluation. Based on the experimental conclusions, modifications are made to our algorithm to further verify the correctness of our findings. All experimental results are deduced based on the CEC2017 benchmark problem suite from the IEEE Congress on Evolutionary Computation (CEC).

关键词：

来源：评论

学校读者我要写书评

暂无评论

GROUNDING GRAPH NETWORK SIMULATORS USING PHYSICAL SENSOR OBSERVATIONS 11

GROUNDING GRAPH NETWORK SIMULATORS USING PHYSICAL SENSOR OBS...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Linkerhägner, Jonas Freymuth, Niklas Scheikl, Paul Maria Mathis-Ullrich, Franziska Neumann, Gerhard Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-University Erlangen-Nürnberg Erlangen Germany

Physical simulations that accurately model reality are crucial for many engineering disciplines such as mechanical engineering and robotic motion planning. In recent years, learned Graph Network Simulators produced accurate mesh-based simulations while requiring only a fraction of the computational cost of traditional simulators. Yet, the resulting predictors are confined to learning from data generated by existing mesh-based simulators and thus cannot include real world sensory information such as point cloud data. As these predictors have to simulate complex physical systems from only an initial state, they exhibit a high error accumulation for long-term predictions. In this work, we integrate sensory information to ground Graph Network Simulators on real world observations. In particular, we predict the mesh state of deformable objects by utilizing point cloud data. The resulting model allows for accurate predictions over longer time horizons, even under uncertainties in the simulation, such as unknown material properties. Since point clouds are usually not available for every time step, especially in online settings, we employ an imputation-based model. The model can make use of such additional information only when provided, and resorts to a standard Graph Network Simulator, otherwise. We experimentally validate our approach on a suite of prediction tasks for mesh-based interactions between soft and rigid bodies. Our method results in utilization of additional point cloud information to accurately predict stable simulations where existing Graph Network Simulators fail. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Data augmentation and denoising of computed tomography scan images in training deep learning models for rapid COVID-19 detection

引用

International Journal of Business intelligence and Data Mining 2024年第2期24卷 203-216页

作者： Mubarak, Auwalu Saleh Serte, Sertan Al-Turjman, Fadi Ameen, Zubaida Sa'Id Artificial Intelligence Engineering Department AI and Robotics Institute Near East University Mersin10 Turkey Research Center for AI and IoT Faculty of Engineering University of Kyrenia Mersin10 Turkey Department of Electrical and Electronics Engineering Near East University Mersin10 Turkey

The deadly respiratory disease corona virus-2 (COVID-19) which was declared a pandemic by the World Health Organization (WHO) has resulted in over a million deaths around the world within less than a year. With the rapid spread of the virus, the currently adopted COVID-19 test by the WHO is the reverse transcription polymerase chain reaction (RT-PCR) test, which is expensive, time-consuming and not accessed by underdeveloped countries. Computed tomography (CT) scan images that were used in profiling suspected COVID-19 patients can serve as an alternative to the RT PCR test method. In this study, two different pre-Trained deep learning models ResNet-50 and ResNet-101 were trained to classify positive COVID-19 scan images. The best model which was trained on the augmented CT scan images achieved an accuracy of 98.3%, a sensitivity of 0.984, specificity of 0.983. © 2024 Inderscience Enterprises Ltd.. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Through the Rubble: Discovering the Invisible

Through the Rubble: Discovering the Invisible

引用

International Conference on Control, Automation, robotics and Vision (ICARCV)

作者： Yogesh Dasgaonkar Radhe Shyam Sharma Centre for Artificial Intelligence and Robotics at Indian Institute of technology Mandi India

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

To rescue human life trapped beneath the rubble (invisible to human or visual sensors) in the aftermath of an earthquake, we propose a human signature-based system that does three things efficiently - detects human life, its location, and the safe rescue path. This work has two novel contributions: a) The multi-robot rescue team equipped with our designed WiFi-based transmitter-receiver system to inspect the calamity site and detect human life without entering the rubble. b) The real-world earthquake rubble data is sparsely available and varies uncertainly across countries. We propose a system to collect human signatures unobtrusively pre-calamity, which helps in accurate human life detection post-calamity. We handle the data sparsity and uncertainty problem by proposing data decomposition and Variational Autoencoding (VAE) methods on the signature data. The results we achieve in a real-world calamity site set up with an Unmanned Ground Vehicle (UGV), drone, and robot manipulator system are promising as we can detect human life with 82% accuracy.

关键词： Visualization Accuracy Uncertainty Disasters Earthquakes Manipulators Sensor systems Land vehicles Sensors Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Targeted Context Attack for Object Detection

SSRN

引用

SSRN 2024年

作者： Sun, Changfeng Zhang, Xuchong Han, Haoliang Sun, Hongbin Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

Compared to the untargeted attack, the targeted attack is a more challenging task in the field of adversarial attacks for object detection, because it aims to mislead the detectors to predict certain specific wrong labels rather than arbitrary labels. The existing targeted attack methods are primarily implemented by maximizing the classification score of the target object, resulting in a poor fooling rate, especially in the case of a large gap between the correct label and the specified wrong label of the victim object. Considering the significant impact of contextual information on object detection, it is difficult to mislabel the victim object to a designated object which has low association with the original context. Therefore, we design a classification network to model the contextual information and propose a Targeted Context Attack method which changes not only the classification score of the victim object itself, but also the score of its context. The extensive experiments on MS COCO and VOC datasets using YOLOv3 and Faster RCNN show that the targeted context attack largely improves the fooling rate of targeted attack for object detection in terms of both white-box and black-box cases, even if the target object is totally dissimilar with the victim object. Specifically, the proposed attack method at most achieves a 21.8% improvement in the fooling rate for attacking YOLOv3. © 2024, The Authors. All rights reserved.

关键词： Object detection

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：