检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

575 篇 会议
15 册 图书
4 篇 期刊文献

馆藏范围

594 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

480 篇 工学
- 454 篇 计算机科学与技术...
- 127 篇 软件工程
- 85 篇 电气工程
- 45 篇 信息与通信工程
- 30 篇 控制科学与工程
- 15 篇 机械工程
- 15 篇 生物工程
- 10 篇 光学工程
- 7 篇 化学工程与技术
- 7 篇 航空宇航科学与技...
- 7 篇 生物医学工程（可授...
- 6 篇 建筑学
- 5 篇 土木工程
- 5 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
153 篇 理学
- 113 篇 物理学
- 23 篇 数学
- 15 篇 生物学
- 11 篇 统计学（可授理学、...
- 5 篇 系统科学
- 4 篇 化学
40 篇 管理学
- 21 篇 管理科学与工程(可...
- 20 篇 图书情报与档案管...
- 6 篇 工商管理
15 篇 医学
- 9 篇 基础医学(可授医学...
- 9 篇 临床医学
14 篇 教育学
- 14 篇 教育学
13 篇 法学
- 7 篇 社会学
- 6 篇 法学
4 篇 经济学
- 4 篇 应用经济学
4 篇 农学
4 篇 军事学

主题

144 篇 machine learning
105 篇 artificial intel...
65 篇 deep learning
28 篇 adversarial mach...
24 篇 reinforcement le...
16 篇 object detection
15 篇 learning systems
14 篇 neural networks
14 篇 federated learni...
13 篇 computer vision
12 篇 cybersecurity
12 篇 security
12 篇 accuracy
12 篇 machine learning...
12 篇 training
11 篇 computer applica...
10 篇 multi-domain ope...
9 篇 ai
9 篇 explainable arti...
9 篇 unsupervised lea...

机构

6 篇 marwadi universi...
6 篇 national univers...
5 篇 us army engineer...
5 篇 us army res lab ...
4 篇 college of compu...
4 篇 siemens corporat...
4 篇 univ maryland co...
4 篇 carnegie mellon ...
4 篇 foundation for r...
3 篇 mcmaster univ 12...
3 篇 korea univ dept ...
3 篇 us mil acad army...
3 篇 ibm tj watson re...
2 篇 johns hopkins un...
2 篇 penn state univ ...
2 篇 the high school ...
2 篇 howard univ wash...
2 篇 wroclaw universi...
2 篇 univ southern ca...
2 篇 shanghai ai lab ...

作者

8 篇 rawat danda b.
6 篇 divyakant meva
6 篇 kalpesh popat
6 篇 sunil bajeja
6 篇 pankaj mudholkar
6 篇 sridaran rajagop...
4 篇 surucu onur
4 篇 giuliano alessan...
4 篇 alsadi naseem
4 篇 helmut degen
4 篇 hilal waleed
4 篇 stavroula ntoa
4 篇 raglin adrienne
4 篇 asher derrik e.
4 篇 yawney john
4 篇 markowitz jared
3 篇 bastian nathanie...
3 篇 schutte klamer
3 篇 kwak heon-gyu
3 篇 price stanton r.

语言

564 篇 英文
30 篇 其他
2 篇 中文

检索条件"任意字段=Conference on Artificial Intelligence and Machine Learning in Defense Applications IV"

共 594 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

artificial intelligence and machine learning in defense applications iv

Artificial Intelligence and Machine Learning in Defense Appl...

引用

artificial intelligence and machine learning in defense applications iv 2022

ISBN: (纸本)9781510655553

The proceedings contain 18 papers. The topics discussed include: dynamic-automatic pipelines for finding topic-specific information clusters using NLP methods in connection with a model-driven approach;a smart embedded imaging system for true color face analysis;action recognition algorithm from visual sensor data for contactless robot control systems;automated example selection for iterative training of annotation networks;learning without gradients: multi-agent reinforcement learning approach to optimization;meaningful machine learning robustness evaluation in real-world machine learning enabled system contexts;evaluating active learning methods for synthetic aperture radar maritime object detection;performance metrics with operational context for video object detection algorithms;comparative evaluations of online and offline visual tracking algorithms;and ARORA and NavSim: a simulator system for training autonomous agents with geospecific data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simplicity Bias in Overparameterized machine learning 38

Simplicity Bias in Overparameterized Machine Learning

引用

38th AAAI conference on artificial intelligence (AAAI) / 36th conference on Innovative applications of artificial intelligence / 14th Symposium on Educational Advances in artificial intelligence

作者： Berchenko, Yakir Ben Gurion Univ Negev Dept Ind Engn & Management POB 653 IL-84105 Beer Sheva Israel

ISBN: (纸本)1577358872

A thorough theoretical understanding of the surprising generalization ability of deep networks (and other overparameterized models) is still lacking. Here we demonstrate that simplicity bias is a major phenomenon to be reckoned with in overparameterized machine learning. In addition to explaining the outcome of simplicity bias, we also study its source: following concrete rigorous examples, we argue that (i) simplicity bias can explain generalization in overparameterized learning models such as neural networks;(ii) simplicity bias and excellent generalization are optimizer-independent, as our examples show, and although the optimizer affects training, it is not the driving force behind simplicity bias;(iii) simplicity bias in pre-training models, and subsequent posteriors, is universal and stems from the subtle fact that uniformly-at-random constructed priors are not uniformly-at-random sampled;and (iv) in neural network models, the biasing mechanism in wide (and shallow) networks is different from the biasing mechanism in deep (and narrow) networks.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Attack and defense for Reinforcement learning 38

Optimal Attack and Defense for Reinforcement Learning

引用

38th AAAI conference on artificial intelligence (AAAI) / 36th conference on Innovative applications of artificial intelligence / 14th Symposium on Educational Advances in artificial intelligence

作者： McMahan, Jeremy Wu, Young Zhu, Xiaojin Xie, Qiaomin Univ Wisconsin Madison WI 53706 USA

ISBN: (纸本)1577358872

To ensure the usefulness of Reinforcement learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external attacker has the power to manipulate the victim agent's interaction with the environment. We study the full class of online manipulation attacks, which include (i) state attacks, (ii) observation attacks (which are a generalization of perceived-state attacks), (iii) action attacks, and (iv) reward attacks. We show the attacker's problem of designing a stealthy attack that maximizes its own expected reward, which often corresponds to minimizing the victim's value, is captured by a Markov Decision Process (MDP) that we call a meta-MDP since it is not the true environment but a higher level environment induced by the attacked interaction. We show that the attacker can derive optimal attacks by planning in polynomial time or learning with polynomial sample complexity using standard RL techniques. We argue that the optimal defense policy for the victim can be computed as the solution to a stochastic Stackelberg game, which can be further simplified into a partially-observable turn-based stochastic game (POTBSG). Neither the attacker nor the victim would benefit from deviating from their respective optimal policies, thus such solutions are truly robust. Although the defense problem is NP-hard, we show that optimal Markovian defenses can be computed (learned) in polynomial time (sample complexity) in many scenarios.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Constrained deep reinforcement learning for maritime platform defense 6

Constrained deep reinforcement learning for maritime platfor...

引用

conference on artificial intelligence and machine learning for Multi-Domain Operations applications VI

作者： Markowitz, Jared Johns Hopkins Univ Appl Phys Lab Laurel MD 20723 USA

ISBN: (纸本)9781510674219;9781510674202

We present a method for maritime platform defense using constrained deep reinforcement learning (DRL), showing how competing desires to reliably defend a fleet and conserve inventory may be managed through a dual optimization strategy. Against persistent and variable raids of threats, our agents minimize inventory expenditure subject to a constraint on the average time before a threat impacts the fleet being defended. Critically, the additional inventory consideration is introduced only after the agent has learned to defend the fleet well enough to consistently satisfy the constraint. In evaluations against a realistic simulation environment and with variable multi-ship geometries, we find that our strategy may be tuned to either (1) enable the agent to make significant gains in efficiency while losing very little in terms of reliability or (2) closely track specified reliability constraints while reducing inventory expenditure even further. The result is an agent with considerably stronger long-term viability, since the conserved inventory may be used for future engagements. We speculate on the potential of this method to provide a tunable, trustworthy artificial assistant to human decision-makers tasked with defense scheduling.

关键词： Deep Reinforcement learning Maritime Platform defense Constrained Reinforcement learning AI Safety

来源：评论

学校读者我要写书评

暂无评论

SAME: Sample Reconstruction against Model Extraction Attacks 38

SAME: Sample Reconstruction against Model Extraction Attacks

引用

38th AAAI conference on artificial intelligence (AAAI) / 36th conference on Innovative applications of artificial intelligence / 14th Symposium on Educational Advances in artificial intelligence

作者： Xie, Yi Zhang, Jie Zhao, Shiqian Zhang, Tianwei Chen, Xiaofeng Xidian Univ Xian Peoples R China Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)1577358872

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, machine learning as a Service (MLaaS) has emerged, lowering the barriers for users to release or productize their deep learning models. However, previous studies have highlighted potential privacy and security concerns associated with MLaaS, and one primary threat is model extraction attacks. To address this, there are many defense solutions but they suffer from unrealistic assumptions and generalization issues, making them less practical for reliable protection. Driven by these limitations, we introduce a novel defense mechanism, SAME, based on the concept of sample reconstruction. This strategy imposes minimal prerequisites on the defender's capabilities, eliminating the need for auxiliary Out-of-Distribution (OOD) datasets, user query history, white-box model access, and additional intervention during model training. It is compatible with existing active defense methods. Our extensive experiments corroborate the superior efficacy of SAME over state-of-the-art solutions. Our code is available at https://***/xythink/SAME.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Joint Human and Autonomy Teaming for defense: Status, Challenges, and Perspectives 5

Joint Human and Autonomy Teaming for Defense: Status, Challe...

引用

conference on artificial intelligence and machine learning for Multi-Domain Operations applications V

作者： El Alami, Hassan Nwosu, Mary Rawat, Danda B. Howard Univ Washington DC 20059 USA

ISBN: (数字)9781510661936

ISBN: (纸本)9781510661929;9781510661936

Human and Autonomy Teaming (HAT) involves humans, artificial intelligence and machine learning (AI/ML), and autonomous systems (AS) working together to enhance performance and efficiency across a variety of fields. The purpose of this paper is to outline the current status, challenges, and perspectives related to HAT in the defense applications, such as multi-domain operations (MDOs). This paper emphasizes that, although ASs have numerous benefits, humans, and machines need to work together to ensure effective communication and coordination. Furthermore, this paper addresses the issues of situation awareness, HAT bias, security, privacy, confidentiality, trust, transparency, and explainability as they relate to joint HAT in MDOs. Finally, this paper explores the potential of perspectives to overcome these challenges and enhance collaboration between humans, AI/ML, and AS in the context of defense.

关键词： Human-machine Interaction Human-Autonomy Teaming Multi-Domain Operations Autonomous Systems artificial intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Fine-Grained Automatic Target Recognition through Active learning for defense applications 6

Efficient Fine-Grained Automatic Target Recognition through ...

引用

conference on artificial intelligence and machine learning for Multi-Domain Operations applications VI

作者： Thorp, Claire A. Sisti, Sean P. Browne, Lesrene A. Schwartz, Casey Inkawhich, Nathan Bennette, Walter Air Force Res Lab Informat Directorate Rome NY 13441 USA Northeastern Univ Boston MA USA

ISBN: (纸本)9781510674219;9781510674202

Out of distribution (OOD) detection has shown immense promise to enable Automatic Target Recognition models for defense applications. However, many defense applications have constraints that make current best practices for training OOD detection models challenging. These include: the need to perform fine-grained classification of identified targets, low amounts of labeled data to train models, limited availability of Subject Matter Experts to accurately label new data, and the potential need to incorporate new classes of targets as they are discovered. Given these constraints, we propose to build a fine-grained classifier with robustness against OOD data through an active learning approach - designed to further classify objects after detection through some coarse-grained object detection model. This paper will explore active learning methods for Automatic Target Recognition applications, with experiments conducted using the fine-grained overhead imagery dataset, ShipsRSImageNet, along with samples from the DOTA dataset as an exposure set. Our contributions will include recommendations to achieve fine-grained Automatic Target Recognition with robustness against OOD data with minimal labeling from Subject Matter Experts.

关键词： Out of Distribution Active learning BADGE Image Classification Batch Active learning

来源：评论

学校读者我要写书评

暂无评论

Responsible artificial intelligence and Bias Mitigation in Deep learning Systems 27

Responsible Artificial Intelligence and Bias Mitigation in D...

引用

27th International conference on Information Visualisation (iv) / 19th International conference Computer Graphics, Imaging and Visualization (CGiv)

作者： Gavrilova, Marina L. Univ Calgary Comp Sci Dept Calgary AB Canada

ISBN: (纸本)9798350341614

Responsible, ethical and trustworthy decision making powered by the new generation of artificial intelligence (AI) and deep learning (DL) recently emerged as one of the key societal challenges. The tutorial discusses key challenges, lists major applications, presents mitigation strategies and provides insights on the future developments in this emerging research domain.

关键词： artificial intelligence Deep learning responsible AI ethics algorithmic fairness bias mitigation visual knowledge discovery biometrics decision-making

来源：评论

学校读者我要写书评

暂无评论

The Prediction Management Framework: Ethical, Governable, and Interpretable Deployment of artificial intelligence/machine learning Systems 4

The Prediction Management Framework: Ethical, Governable, an...

引用

conference on artificial intelligence and machine learning for Multi-Domain Operations applications iv

作者： Grahn, Daniel Richey, Melonie Altamira 8201 Greensboro Dr St 800 Mclean VA 22102 USA

ISBN: (纸本)9781510651036;9781510651029

As defense organizations integrate artificial intelligence (AI) into evermore critical operations, especially those near the tactical edge with real-time decision making, the necessity of a standardized, robust framework for deployment and management of AI systems is increasing. In this paper, we propose a Prediction Management Framework (PMF) that aligns with the Department of defense's Ethical Principles for AI for ethical, governable, and interpretable deployments. We explore different requirements for the framework with inspiration drawn from various regulatory, safety, and communication standards. In support of these requirements, we offer recommendations and implementation guidance to provide comprehensive visibility into the system.

关键词： artificial intelligence Deployment DoD Ethical principles for AI Prediction Nutrition Facts Prediction Identification Prediction Verification

来源：评论

学校读者我要写书评

暂无评论

learning Behavior of Offline Reinforcement learning Agents 6

Learning Behavior of Offline Reinforcement Learning Agents

引用

conference on artificial intelligence and machine learning for Multi-Domain Operations applications VI

作者： Shukla, Indu Dozier, Haley. R. Henslee, Althea. C. US Army Engn Res & Dev Ctr 3909 Halls Ferry Rd Vicksburg MS 39180 USA

ISBN: (纸本)9781510674219;9781510674202

Reinforcement learning (RL) agents offer significant value for military applications by effectively navigating complex, dynamic environments typical of mission engineering and operational analysis. Once trained, these agents can be employed to inform mission planners on optimal strategies, tactics, or even innovative utilization of different military platforms within a given scenario. In recent years, RL has become a major research area for automation and solving complex sequential decision-making problems. However, a notable challenge lies in the inherent black-box nature of RL models and their inability to explain their decisions and actions. This limitation serves as a major adoption barrier, especially in defense. This paper aims to study EXplainable RL (XRL) within an operational context. XRL is a distinct branch of Explainable artificial intelligence (XAI) techniques that provides the necessary transparency to make AI models more transparent to address this challenge. This research is an effort to gain insight into the behavior of RL agents in an operational environment and to discuss explainability and interpretability through the lens of different roles within the decision-making pipeline.

关键词： Offline Reinforcement learning Explainability XAI XRL LIME SHAP

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共60页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：