检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Sangha Park Jisoo Mok Dahuin Jung Saehyung Lee Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

Successful detection of Out-of-Distribution (OoD) data is becoming increasingly important to ensure safe deployment of neural networks. One of the main challenges in OoD detection is that neural networks output overconfident predictions on OoD data, make it difficult to determine OoD-ness of data solely based on their predictions. Outlier exposure addresses this issue by introducing an additional loss that encourages low-confidence predictions on OoD data during training. While outlier exposure has shown promising potential in improving OoD detection performance, all previous studies on outlier exposure have been limited to utilizing visual outliers. Drawing inspiration from the recent advancements in vision-language pre-training, this paper venture out to the uncharted territory of textual outlier exposure. First, we uncover the benefits of using textual outliers by replacing real or virtual outliers in the image-domain with textual equivalents. Then, we propose various ways of generating preferable textual outliers. Our extensive experiments demonstrate that generated textual outliers achieve competitive performance on large-scale OoD and hard OoD benchmarks. Furthermore, we conduct empirical analyses of textual outliers to provide primary criteria for designing advantageous textual outliers: near-distribution, descriptiveness, and inclusion of visual semantics. Code is available at https://***/wiarae/TOE

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reachability Analysis of Nonlinear Discrete-Time Systems Using Polyhedral Relaxations and Constrained Zonotopes 63

Reachability Analysis of Nonlinear Discrete-Time Systems Usi...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Rego, Brenner S. Raffo, Guilherme V. Terra, Marco H. Scott, Joseph K. Georgia Institute of Technology Department of Chemical and Biomolecular Engineering 311 Ferst Dr. AtlantaGA30318 United States University of Säo Paulo Department of Electrical and Computer Engineering SP Säo Carlos13566-590 Brazil Federal University of Minas Gerais Department of Electronics Engineering and the Graduate Program in Electrical Engineering MG Belo Horizonte31270-901 Brazil

ISBN: (纸本)9798350316339

This paper presents a novel algorithm for reachability analysis of nonlinear discrete-time systems. The proposed method combines constrained zonotopes (CZs) with polyhedral relaxations of factorable representations of nonlinear functions to propagate CZs through nonlinear functions, which is normally done using conservative linearization techniques. The new propagation method provides better approximations than those resulting from linearization procedures, leading to significant improvements in the computation of reachable sets in comparison to other CZ methods from the literature. Numerical examples highlight the advantages of the proposed algorithm. © 2024 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Classification and tracking of items on a moving conveyor belt using convolutional networks and image processing

Classification and tracking of items on a moving conveyor be...

引用

Artificial Intelligence, computer, Data Sciences and Applications (ACDSA), International Conference on

作者： Angelo Leite Medeiros De Góes Adrião Duarte Dória Neto Matheus Gomes Diniz Andrade Thiago Theiry De Oliveira Electrical and Computer Engineering Postgraduate Program Federal University of Rio Grande do Norte Natal Brazil Computer Engineering Federal University of Rio Grande do Norte Natal Brazil

The prolonged waiting time at supermarket checkout lines poses a significant challenge to the shopping experience, impacting customer satisfaction and operational efficiency. This paper presents a prototype that addresses this issue by utilizing computer vision and deep learning. The model, incorporating convolutional neural networks such as YOLO v4 tiny and YOLO v5 small, along with tools like OpenCV and Roboflow for dataset management, achieves a remarkable 98% mean average precision for two-class detection. It efficiently detects, classifies, tracks, and counts items on a mobile supermarket conveyor belt. Additionally, we introduce a versatile framework designed for seamless integration into real-world applications. It comprises a customizable monitoring application and simulator that facilitates synthetic image data generation. Managing diverse items in a supermarket presents a major challenge for data gathering, labeling, and training. In that sense, the importance of customizable monitoring and simulation tools is highlighted, emphasizing their practical role. Our findings demonstrate the feasibility of maintaining a minimal 0% to 2.85% precision tradeoff while using half of the data as synthetic for two-class detection, indicating potential practicality in supermarkets with proper scaling. In summary, this study brings tangible benefits to both customers and retailers, offering a potential to streamline, speed up, and cut costs in the supermarket checkout process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Expanded Latent Space Autoencoder for Land Cover Classification of Remote Sensing Images from EuroSAT

An Expanded Latent Space Autoencoder for Land Cover Classifi...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Emerson Vilar Oliveira Luiz Marcos Garcia Gonçalves Graduate Program in Electrical and Computer Engineering Universidade Federal do Rio Grande do Norte Natal Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

Image classification has been instrumental in the interpretation and labeling of images in the field of remote sensing, computer vision, and in robotics applications. Machine learning and artificial intelligence algorithms, particularly artificial neural networks, are extensively utilized for this purpose. In this work we propose the Expanded Latent Space Autoencoder (ELSA) with a case use application to classify land cover data. The main idea on the ELSA network structure is to utilize the latent spaces of multiple internal autoencoders in order to create an expanded latent space. This expanded latent space extracts more information from the input data, and serves as input features for a more simpler classifier network. In order to evaluate the proposed network's ability to extract features and classify complex and multispectral images we employed it to the EuroSAT dataset. The results demonstrate a remarkable capacity for feature extraction using the ELSA network, with lower complexity, trained with a reduced number of images. The classifier network achieved a final accuracy of 98.7%, matching or exceeding the performance of more complex state-of-the-art models.

关键词： Machine learning algorithms Instruments Autoencoders Land surface Machine learning Feature extraction Robot sensing systems Labeling Remote sensing Image classification

来源：评论

学校读者我要写书评

暂无评论

Deterministic Quantum Repeater with Single Atoms in Cavities

arXiv

引用

arXiv 2024年

作者： Lei, Yisheng Department of Electrical and Computer Engineering and Applied Physics Program Northwestern University EvanstonIL60208 United States

Efficient quantum repeaters are needed to combat photon losses in fibers in future quantum networks. Single atom coupled with photonic cavity offer a great platform for photon-atom gate. Here I propose a quantum repeater scheme with deterministic entanglement generation and entanglement swapping based on photon-atom gates. It can be implemented with various types of atomic systems and require much less experimental complexity compared with other repeater protocols. With current available experimental techniques and reasonable improvements, high entanglement distribution rates can be achieved. A multiplexing configuration of 5-10 single atoms in cavities, secret key rates in order of 100s Hz to kHz can be achieved for communication distance of 1000km, and a few Hz to 10s Hz can be achieved for communication distance of 10000km with longer atomic coherence time and lower photon-atom gate error rate. This proposal paves the way to demonstrate efficient entanglement distribution with quantum repeaters in near future. © 2024, CC BY.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Spirograph Method and Reconfigurable Intelligent Surface for Future Communication Systems

Joint Design of Spirograph Method and Reconfigurable Intelli...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Yafis, Balqis Huang, Jane-Hwa Yu, Chih-Min Wang, Li-Chun National Yang Ming Chiao Tung University Eecs Int'l Graduate Program Hsinchu Taiwan National Chi Nan University Dept. of Electrical Engineering Nantou County Taiwan Chung Yuan Christian University Department of Information and Computer Engineering Taoyuan City Taiwan

ISBN: (纸本)9798350351255

Reconfigurable Intelligent Surface (RIS) is a transformative technology using the passive beamforming capabilities to create the program.able wireless environments. However, the control overhead is a challenging issue. The system needs to deliver the high-precision reflection coefficients to the RIS controller, for adjusting the phase shifts of the numerous RIS elements. Therefore, we propose a Spirograph-based discrete beamdirection strategy, which selects a set of non-uniformly distributed beam directions based on the generic patterns generated by the Spirograph (SG). We evaluate the achievable data rate and the number of controlling bits of SG-based method. We compare the SG-based method, the ideal continuous phase-shift method, and the SISO method. Simulation results show that with the properly-selected discrete beam directions, the SG-based method can achieve a comparable data rate as the ideal method, while having a lower control overhead. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

KenCoh: A Ranked-Based Canonical Coherence 1

arXiv

引用

arXiv 2024年

作者： Talento, Mara Sherlin D.P. Roy, Sarbojit Ombao, Hernando Statistics Program Computer Electrical and Mathematical Science & Engineering King Abdullah University of Science and Technology Saudi Arabia

In this paper, we consider the problem of characterizing a robust global dependence between two brain regions where each region may contain several voxels or channels. This work is driven by experiments to investigate the dependence between two cortical regions and to identify differences in brain networks between brain states, e.g., alert and drowsy states. The most common approach to explore dependence between two groups of variables (or signals) is via canonical correlation analysis (CCA). However, it is limited to only capturing linear associations and is sensitive to outlier observations. These limitations are crucial because brain network connectivity is likely to be more complex than linear and that brain signals may exhibit heavy-tailed properties. To overcome these limitations, we develop a robust method, Kendall canonical coherence (KenCoh), for learning monotonic connectivity structure among neuronal signals filtered at given frequency bands. Furthermore, we propose the KenCoh-based permutation test to investigate the differences in brain network connectivity between two different states. Our simulation study demonstrates that KenCoh is competitive to the traditional variance-covariance estimator and outperforms the later when the underlying distributions are heavy-tailed. We apply our method to EEG recordings from a virtual-reality driving experiment. Our proposed method led to further insights on the differences of frontal-parietal cross-dependence network when the subject is alert and when the subject is drowsy and that left-parietal channel drives this dependence at the beta-band. © 2024, CC BY.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Introducing spectral attention for long-range dependency in time series forecasting 24

Introducing spectral attention for long-range dependency in ...

引用

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

作者： Bong Gyun Kang Dongjun Lee HyunGi Kim DoHyun Chung Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Department of Future Automotive Mobility Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

ISBN: (纸本)9798331314385

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent inability to effectively address long-range dependencies in time series data, primarily due to using fixed-size inputs for prediction. Furthermore, they typically sacrifice essential temporal correlation among consecutive training samples by shuffling them into mini-batches. To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure. Spectral Attention preserves long-period trends through a low-pass filter and facilitates gradient to flow between samples. Spectral Attention can be seamlessly integrated into most sequence models, allowing models with fixed-sized look-back windows to capture longrange dependencies over thousands of steps. Through extensive experiments on 11 real-world time series datasets using 7 recent forecasting models, we consistently demonstrate the efficacy of our Spectral Attention mechanism, achieving state-of-the-art results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectral learning of shared dynamics between generalized-linear processes 24

Spectral learning of shared dynamics between generalized-lin...

引用

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

作者： Lucine L. Oganesian Omid G. Sani Maryam M. Shanechi Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles CA Ming Hsieh Department of Electrical and Computer Engineering Thomas Lord Department of Computer Science Alfred E. Mann Department of Biomedical Engineering Neuroscience Graduate Program University of Southern California Los Angeles CA

ISBN: (纸本)9798331314385

Generalized-linear dynamical models (GLDMs) remain a widely-used framework within neuroscience for modeling time-series data, such as neural spiking activity or categorical decision outcomes. Whereas the standard usage of GLDMs is to model a single data source, certain applications require jointly modeling two generalized-linear time-series sources while also dissociating their shared and private dynamics. Most existing GLDM variants and their associated learning algorithms do not support this capability. Here we address this challenge by developing a multi-step analytical subspace identification algorithm for learning a GLDM that explicitly models shared vs. private dynamics within two generalized-linear time-series. In simulations, we demonstrate our algorithm's ability to dissociate and model the dynamics within two time-series sources while being agnostic to their respective observation distributions. In neural data, we consider two specific applications of our algorithm for modeling discrete population spiking activity with respect to a secondary time-series. In both synthetic and real data, GLDMs learned with our algorithm more accurately decoded one time-series from the other using lower-dimensional latent states, as compared to models identified using existing GLDM learning algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Stability of a Sieve Shaker Used in a Pachouli Oil Refining Process 3rd

Dynamic Stability of a Sieve Shaker Used in a Pachouli Oil R...

引用

3rd International Conference on Experimental and Computational Mechanics in engineering, ICECME 2021

作者： Kurniawan, Rudi Fuadi, Zahrul Abubakar, Fathurrahman Afdhal, Afdhal Department of Mechanical and Industrial Engineering Universitas Syiah Kuala Banda Aceh Indonesia Undergraduate Study Program Department of Mechanical Engineering Universitas Syiah Kuala Banda Aceh Indonesia Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (纸本)9789811936289

One of the problems causing low quality of essential oils is the high content of solvent resulting from traditional extraction process employing low purity metallic components. This extracted oil therefore requires further process to improve the patchouli alcohol content of the oil by removing unwanted components. One of the process is by mixing the oil with bentonite and zeolite. In this study, a sieve shaker is designed to be used at an integrated equipment for patchouli oil refining process. In order to have a dynamically stable shaker, it is necessary to investigate the effect of various components for the stability, particularly the spring stiffness. The simulation was conducted using Autodesk Inventor using a one degree of freedom model. It is shown from the result that, for the defined condition, the sieve shaker shown a stable condition for the spring stiffness value at least 10 kN/m. Spring stiffness lower than the value could cause detachment of the roll follower from the cam, resulting in impact between the components. © 2023, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stiffness

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：