检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Han, Liying dong, Gaofeng Ouyang, Xiaomin Kaplan, Lance Cerutti, Federico Srivastava, Mani Department of Electrical and Computer Engineering University of California Los Angeles United States Department of Computer Science and Engineering Hong Kong University of Science and Technology China US Army DEVCOM Army Research Laboratory United States Department of Information Engineering University of Brescia Italy Amazon United States

Current machine learning models excel in short-span perception tasks but struggle to derive high-level insights from long-term observation, a capability central to understanding complex events (CEs). CEs, defined as sequences of short-term atomic events (AEs) governed by spatiotemporal rules, are challenging to detect online due to the need to extract meaningful patterns from long and noisy sensor data while ignoring irrelevant events. We hypothesize that state-based methods are well-suited for CE detection, as they capture event progression through state transitions without requiring long-term memory. Baseline experiments validate this, demonstrating that the state-space model Mamba outperforms existing architectures. However, Mamba’s reliance on extensive labeled data, which are difficult to obtain, motivates our second hypothesis: decoupling CE rule learning from noisy sensor data can reduce data requirements. To address this, we propose NARCE, a framework that combines Neural Algorithmic Reasoning (NAR) to split the task into two components: (i) learning CE rules independently of sensor data using synthetic concept traces generated by LLMs and (ii) mapping sensor inputs to these rules via an adapter. Our results show that NARCE outperforms baselines in accuracy, generalization to unseen and longer sensor data, and data efficiency, significantly reducing annotation costs while advancing robust CE detection. © 2025, CC BY.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Human-Guided Artificial Intelligence (HGAI), a Framework for Overcoming AI's Blind Spots

Human-Guided Artificial Intelligence (HGAI), a Framework for...

引用

IEEE Southeastcon

作者： Ziyu Chen Selam B. Kelil Mohammad Y. M. Naser Jason S. Metcalfe Sylvia Bhattacharya Electrical & Computer Engineering Department Kennesaw State University Marietta USA Computer Science Department Kennesaw State University Marietta USA US DEVCOM Army Research Laboratory Aberdeen Proving Ground Aberdeen USA Engineering Technology Department Kennesaw State University Marietta USA

ISBN: (数字)9798331504847

ISBN: (纸本)9798331504854

Artificial Intelligence (AI) systems frequently exhibit systematic blind spots, often referred to as hallucinations in Large Language Models (LLMs), posing risks in high-stakes applications such as autonomous systems, security, and military operations. This paper explores how human intuitive responses, along with conscious reasoning processes, can be integrated to mitigate AI blind spots and enhance decision-making effectiveness within Human-AI teams. We introduce Human-Guided Artificial Intelligence (HGAI) as a framework for achieving this goal. Specifically, we examine the role of System-1 intuitive processing, as captured through physiological signals such as electroencephalography (EEG) and electrocardiography (ECG), System-2 reasoning-based decision-making, and Multi-Modal Fusion (MMF) mechanisms while assessing the knowledge required to develop more reliable, context-aware, and ethically aligned intelligent decision-making systems for highly complex environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-Robot Coordination through Locality-Based Factorized Multi-Agent Actor-Critic Algorithm

arXiv

引用

arXiv 2025年

作者： Shek, Chak Lam Bedi, Amrit Singh Basak, Anjon Novoseller, Ellen Waytowich, Nick Narayanan, Priya Manocha, dinesh Tokekar, Pratap Department of Electrical and Computer Engineering University of Maryland College ParkMD United States Department of Computer Science University of Central Florida FL United States DEVCOM US Army Research Laboratory AdelphiMD United States Department of Computer Science University of Maryland College ParkMD United States

In this work, we present a novel cooperative multiagent reinforcement learning method called Locality based Factorized Multi-Agent Actor-Critic (Loc-FACMAC). Existing state-of-the-art algorithms, such as FACMAC, rely on global reward information, which may not accurately reflect the quality of individual robots’ actions in decentralized systems. We integrate the concept of locality into critic learning, where strongly related robots form partitions during training. Robots within the same partition have a greater impact on each other, leading to more precise policy evaluation. Additionally, we construct a dependency graph to capture the relationships between robots, facilitating the partitioning process. This approach mitigates the curse of dimensionality and prevents robots from using irrelevant information. Our method improves existing algorithms by focusing on local rewards and leveraging partition-based learning to enhance training efficiency and performance. We evaluate the performance of Loc-FACMAC in three environments: Hallway, Multi-cartpole, and Bounded-Cooperative-Navigation. We explore the impact of partition sizes on the performance and compare the result with baseline MARL algorithms such as LOMAQ, FACMAC, and QMIX. The experiments reveal that, if the locality structure is defined properly, Loc-FACMAC outperforms these baseline algorithms up to 108%, indicating that exploiting the locality structure in the actor-critic framework improves the MARL performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Human-Guided Artificial Intelligence (HGAI), a Framework for Overcoming AI's Blind Spots

Human-Guided Artificial Intelligence (HGAI), a Framework for...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Chen, Ziyu Kelil, Selam B. Naser, Mohammad Y. M. Metcalfe, Jason S. Bhattacharya, Sylvia Kennesaw State University Electrical & Computer Engineering Department Marietta United States Kennesaw State University Computer Science Department Marietta United States Us Devcom Army Research Laboratory Aberdeen Proving Ground Aberdeen United States Kennesaw State University Engineering Technology Department Marietta United States

ISBN: (纸本)9798331504847

关键词： Artificial Intelligence (AI) Human-AI Teams Multi-Modal Fusion (MMF) Physiological Signals

来源：评论

学校读者我要写书评

暂无评论

Atomic layer deposited alumina for use as an etch barrier against xenon difluoride etching

Atomic layer deposited alumina for use as an etch barrier ag...

引用

2010 Solid-State Sensors, Actuators, and Microsystems Workshop

作者： Smith, Gabriel L. Polcawich, Ronald G. Pulskamp, Jeffrey S. Waggoner, Todd Conley, John F. US Army Research Laboratory AdelphiMD United States Oregon State University Electrical Engineering and Computer Science CorvallisOR United States

ISBN: (纸本)0964002485

Xenon difluoride (XeF2) isotropic etching is widely used to release silicon MEMS parts. To realize more complex devices using silicon-on-insulator (SOI) wafers requires the use of a conformal coating of patterned photoresist to selectively protect the device layer Si during the isotropic etch release of the handle wafer. As an alternative to the photoresist protective layer, an ion-mill patterned atomic layer deposited (ALd) alumina (Al2O3) layer was investigated to dramatically improve device yields, particularly in avoiding edge defects and corner pinholes resulting in unintended etching of the silicon. Promising results have been obtained using 25 nm – 200 nm layers of alumina on deeply etched silicon features. This will enable the fabrication of new MEMS silicon devices with reduced feature size for improved performance. © 2010TRF.

关键词： Alumina

来源：评论

学校读者我要写书评

暂无评论

An EEG artifact identification embedded system using ICA and multi-instance learning 50

An EEG artifact identification embedded system using ICA and...

引用

50th IEEE International Symposium on Circuits and Systems, ISCAS 2017

作者： Jafari, Ali Gandhi, Sunil Konuru, Sri Harsha david Hairston, W. Oates, Tim Mohsenin, Tinoosh Department of Computer Science and Electrical Engineering University of Maryland Baltimore County United States Human Research and Engineering Directorate US Army Research Lab United States

ISBN: (纸本)9781467368520

Electroencephalogram (EEG) data is used for a variety of purposes, including brain-computer interfaces, disease diagnosis, and determining cognitive states. Yet EEG signals are susceptible to noise from many sources, such as muscle and eye movements, and motion of electrodes and cables. Traditional approaches to this problem involve supervised training to identify signal components corresponding to noise so that they can be removed. However these approaches are artifact specific. In this paper, we present a novel software-hardware system that uses a weak supervisory signal to indicate that some noise is occurring, but not what the source of the noise is or how it is manifested in the EEG signal. The EEG data is decomposed into independent components using ICA, and these components form bags that are labeled and classified by a multi-instance learning algorithm that can identify the noise components for removal to reconstruct a clean EEG signal. We also performed extensive hyperparameter optimization for the model with the goal of improving accuracy without increasing execution time. This resulted the execution time to be reduced from 282 s to 8.8 s when running the model on an embedded ARM CPU processor at 1.6 GHz clock frequency. In this paper, we present the overall system which includes ICA, SAX and MIL, along with preliminary results for software and hardware implementation when using real EEG data from 64 electrodes. The proposed system consumes 909 mW power during processing above a baseline of 2.32 W idle, while achieving 91.2% artifact identification accuracy. © 2017 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Incorporating background knowledge into video description generation

Incorporating background knowledge into video description ge...

引用

2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

作者： Whitehead, Spencer Ji, Heng Bansal, Mohit Chang, Shih-Fu Voss, Clare R. Computer Science Department Rensselaer Polytechnic Institute Computer Science Department University of North Carolina Chapel Hill United States Department of Electrical Engineering Columbia University United States US Army Research Laboratory United States

ISBN: (纸本)9781948087841

Most previous efforts toward video captioning focus on generating generic descriptions, such as, "A man is talking." We collect a news video dataset to generate enriched descriptions that include important background knowledge, such as named entities and related events, which allows the user to fully understand the video content. We develop an approach that uses video meta-data to retrieve topically related news documents for a video and extracts the events and named entities from these documents. Then, given the video as well as the extracted events and entities, we generate a description using a Knowledge-aware Video description network. The model learns to incorporate entities found in the topically related documents into the description via an entity pointer network and the generation procedure is guided by the event and entity types from the topically related documents through a knowledge gate, which is a gating mechanism added to the model's decoder that takes a one-hot vector of these types. We evaluate our approach on the new dataset of news videos we have collected, establishing the first benchmark for this dataset as well as proposing a new metric to evaluate these descriptions. © 2018 Association for Computational Linguistics

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Frame Selection Strategies for Real-Time Structure-from-Motion from an Aerial Platform

Frame Selection Strategies for Real-Time Structure-from-Moti...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Buck, Andrew R. Akers, Jack d. Anderson, derek T. Keller, James M. Camaioni, Raub deardorff, Matthew Luke, Robert H. University of Missouri Dept. of Electrical Engineering and Computer Science ColumbiaMO United States US Army DEVCOM C5ISR Center Fort BelvoirVA United States

ISBN: (纸本)9798350359527

determining depth from a single camera in motion is a challenging problem that has numerous applications, including autonomous navigation of an unmanned aerial vehicle (UAV). using traditional computer vision techniques such as structure-from-motion (SfM), a depth estimate can be generated using two image pairs from the video stream. The choice of image pairs directly impacts the quality of reconstruction, which is based largely on the camera extrinsics and image features. In this article, we discuss frame selection algorithms to select appropriate image pairs to process for depth estimation. Frames are stored in a rolling buffer, and several measures are computed on potential frame pairs based on camera extrinsics. We use a customized SfM algorithm, Epidepth, which has been designed for handling sequences of aerial imagery with embedded GPS and camera pose metadata. We demonstrate our technique on a simulated dataset created using Unreal Engine and AirSim. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

design of Two-dimensional Polarization Selective computer Generated Holograms using Form-Birefringence

Design of Two-Dimensional Polarization Selective Computer Ge...

引用

diffractive Optics and Micro-Optics, dOMO 2002

作者： Mirotznik, Mark S. Mait, Joseph N. Prather, dennis W. Department of Electrical Engineering and Computer Science The Catholic University of America WashingtonDC20064 United States US Army Research Laboratory 2800 Powder Mill Road AdelphiMD20783-1197 United States Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States

ISBN: (纸本)1557527105

We introduce a new design methodology for synthesizing two-dimensional polarization sensitive computer generated holograms. Our method uses the form-birefringence of a single binary two-dimensional grating to produce different phase profiles for the two orthogonal linear polarizations. We validated the method numerically using the finite-difference-time-domain method. We fabricated a single element but have not yet characterized its performance. © 2002 OSA/dOMO 2002, © 2002 Optical Society of America.

关键词： Finite difference time domain method

来源：评论

学校读者我要写书评

暂无评论

A comparison of ada and pascal in an introductory computer science course 98

A comparison of ada and pascal in an introductory computer s...

引用

1998 Annual ACM SIGAda International Conference on Ada, SIGAda 1998

作者： Murtagh, Jeanne L. Hamilton, John A. Software Professional Development Program Air Force Institute of Technology Wright-Patterson AFBOH45433-7765 United States US Army D/Electrical Engineering and Computer Science United States Military Academy West PointNY10996-1787 United States

ISBN: (纸本)1581130333

Pascal's long and successful run at West Point illustrated Winston Churchill's dictum that, "The absence of alternatives clears the mind wonderfully." However, by the mid-90s, the United States Military Academy was finding that Pascal, long the educational workhorse, was no longer the clear choice for serious computer science education. The decision was taken to evaluate alternatives to Pascal. The criteria selected for programming language evaluation were student learning outcomes based on course goals and objectives. The controlled educational environment of a service academy provides an excellent opportunity to conduct research using control groups and experimental groups. We conducted a side by side comparison of the use of Pascal, which was specifically designed for instructional purposes, and Ada in an introductory course. The experiment demonstrated that students were much more successful in Ada than in Pascal, and led to the revision of the Academy core curriculum to use Ada 95 in our introductory computer science class. This paper discusses the details of our comparison, citing specific examples to illustrate a rational basis for evaluating programming language features against course objectives.

关键词： Students

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：