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

104 篇 学位论文
7 篇 期刊文献
1 篇 会议

馆藏范围

112 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5 篇 工学
- 3 篇 计算机科学与技术...
- 1 篇 仪器科学与技术
- 1 篇 电气工程
- 1 篇 控制科学与工程
- 1 篇 环境科学与工程（可...
3 篇 管理学
- 3 篇 工商管理
- 2 篇 管理科学与工程(可...
2 篇 理学
- 1 篇 化学
- 1 篇 天文学
- 1 篇 大气科学
- 1 篇 地球物理学
- 1 篇 地质学
- 1 篇 生物学
1 篇 教育学
- 1 篇 心理学(可授教育学...

主题

112 篇 artificial intel...
25 篇 other computer s...
17 篇 deep learning
17 篇 computer science...
16 篇 machine learning
14 篇 information secu...
12 篇 databases and in...
6 篇 graphics and hum...
5 篇 theory and algor...
5 篇 computer vision
4 篇 svm
4 篇 neural networks
4 篇 yolo
3 篇 reinforcement le...
3 篇 robotic competit...
3 篇 software enginee...
3 篇 natural language...
3 篇 cnn
3 篇 os and networks
3 篇 bioinformatics

机构

59 篇 san jose state u...
24 篇 university of ma...
2 篇 california polyt...
2 篇 georgia southern...
2 篇 new jersey insti...
2 篇 university of co...
1 篇 amity univ amity...
1 篇 univ nottingham ...
1 篇 western michigan...
1 篇 department of co...
1 篇 wayne state univ...
1 篇 edith cowan univ...
1 篇 univ groningen c...
1 篇 autonomous intel...
1 篇 department of re...
1 篇 univ south pacif...
1 篇 univ chile dept ...
1 篇 university of ne...
1 篇 natl univ sci & ...
1 篇 faculty of envir...

作者

1 篇 ha le thanh
1 篇 ashraf saber
1 篇 komei sugiura
1 篇 niket bhodia
1 篇 anish hemant nar...
1 篇 samanvitha basol...
1 篇 neha atul bhagwa...
1 篇 jr anthony s bus...
1 篇 nicholas a russo
1 篇 preethi sundarav...
1 篇 michael j. brice
1 篇 takeshi takahash...
1 篇 iocchi luca
1 篇 siddharth kumar
1 篇 afaq anam
1 篇 liu yang
1 篇 hurt jason lee
1 篇 muthaiah ramanat...
1 篇 natesh ganesh
1 篇 mehtab iqbal

语言

112 篇 英文

检索条件"主题词=artificial intelligence and robotics"

共 112 条记录，以下是31-40 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：

Efficient Self-supervised Deep Sensorimotor Learning in robotics

Efficient Self-supervised Deep Sensorimotor Learning in Robo...

引用

作者： Takeshi Takahashi University of Massachusetts Amherst

学位级别：博士

Deep learning has been successful in a variety of applications, such as object recognition, video games, and machine translation. Deep neural networks can automatically learn important features given large training datasets. However, the success of deep learning in robotic systems in the real world is still limited mainly because obtaining large datasets and labeling are costly. As a result, much of the successful work in deep learning has been limited to domains where large datasets are readily available or easily collected. To address this issue, I propose a framework for acquiring re-usable skills efficiently combining intrinsic motivation and the control basis framework --- a developmental architecture implemented using a landscape of attractors. A deep neural classifier is used to predict probabilistic control affordances representing controller states accessible by way of actions. Information theoretic motivation with embedding distance influences exploration in a way that supports learning control affordances efficiently. The learned affordance is used as a filter to help a robot experience more positive outcomes of controllers when a robot learns a new affordance. I conduct quantitative experiments using a dynamic simulator and the results show that the proposed learning framework enables a mobile manipulator to learn deep sensorimotor skills more efficiently in a self-supervised learning manner.

关键词： artificial intelligence and robotics Computer Sciences

来源：评论

学校读者我要写书评

暂无评论

From Commands to Goal-Based Dialogs: A Roadmap to Achieve Natural Language Interaction in RoboCup@Home 22nd

From Commands to Goal-Based Dialogs: A Roadmap to Achieve Na...

引用

22nd Annual Robot World Cup International Symposium (RoboCup)

作者： Matamoros, Mauricio Harbusch, Karin Paulus, Dietrich Univ Koblenz Landau Act Vis Grp AGAS Univ Str 1 D-56070 Koblenz Germany

ISBN: (纸本)9783030275440;9783030275433

On the one hand, speech is a key aspect to people's communication. On the other, it is widely acknowledged that language proficiency is related to intelligence. Therefore, intelligent robots should be able to understand, at least, people's orders within their application domain. These insights are not new in RoboCup@Home, but we lack of a long-term plan to evaluate this approach. In this paper we conduct a brief review of the achievements on automated speech recognition and natural language understanding in RoboCup@Home. Furthermore, we discuss main challenges to tackle in spoken human-robot interaction within the scope of this competition. Finally, we contribute by presenting a pipelined road map to engender research in the area of natural language understanding applied to domestic service robotics.

关键词： Robotic competitions Natural language understanding artificial intelligence and robotics

来源：评论

学校读者我要写书评

暂无评论

Game-Assisted Rehabilitation for Post-Stroke Survivors

Game-Assisted Rehabilitation for Post-Stroke Survivors

引用

作者： Hee-Tae Jung University of Massachusetts Amherst

学位级别：博士

Stroke is a leading cause of permanent impairments among its survivors. Although patients need to go through intensive, longitudinal rehabilitation to regain function before the stroke, patients show poor engagement and adherence to rehabilitation therapies which hampers their recovery. As a means to enhance stroke survivors' motivation, engagement, and adherence to intensive and longitudinal rehabilitation, the use of games in stroke rehabilitation has received attention from research and clinical communities. In order to realize this, it is important to take a holistic, end-to-end research approach that encompasses 1) the development of game technologies that are not only entertaining but also rehabilitating or monitoring the functional/impairment level, 2) the quantitative evaluation of the clinical efficacy of the technologies, and 3) the deployment of the technologies in real-world clinical settings to understand if the anticipated clinical efficacy is achieved and how the technologies affect the interaction dynamics among patients, therapists and the technologies. In this dissertation, we introduce our approach to this holistic, end-to-end research for the development, validation, and understanding of real-world use of games in stroke rehabilitation. Towards that end, we designed and developed Neuro-World that can enable accurate, longitudinal assessment of patients' cognitive function outside the clinical setting. The analysis results in the controlled setting show that the proposed approach can accurately assess patients' cognitive function without the help of therapists. While it remains as a future study to deploy Neuro-World in stroke survivors' free-living environments and study the system's impacts on patients' engagement patterns, we use another game platform (i.e., RAPAEL Smart Board) to demonstrate our efforts to understand the real-world interaction dynamics. We investigate the use of the games in the actual hospital setting where the system has bee

关键词： artificial intelligence and robotics Bioinformatics Graphics and Human Computer Interfaces Therapeutics

来源：评论

学校读者我要写书评

暂无评论

Neural Models for Information Retrieval without Labeled Data

Neural Models for Information Retrieval without Labeled Data

引用

作者： Hamed Zamani University of Massachusetts Amherst

学位级别：博士

Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks. Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval. In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or \emph{weakly supervised} solutions for training the models. The proposed learning solutions do not require labeled training data. Instead, in our weak supervision approach, neural models are trained on a large set of noisy and biased training data obtained from external resources, existing models, or heuristics. We first introduce relevance-based embedding models that learn distributed representations for words and queries. We show that the learned representations can be effectively employed for a set of IR tasks, including query expansion, pseudo-relevance feedback, and query classification. We further propose a standalone learning to rank model based on deep neural networks. Our model learns a sparse representation for queries and documents. This enables us to perform efficient retrieval by constructing an inverted index in the learned semantic space. Our model outperforms state-of-the-art retrieval models, while performing as efficiently as term matching retrieval models. We additionally propose a neural network framework for predicting the performance of a retrieval model for a given query. Inspired by existing query performance prediction models, our framework integrates several information sources, such as retrieval score distribution and term distribution in the top retrieved documents. This leads to state-of-the-art results for the performance prediction task on various standard c

关键词： artificial intelligence and robotics Computer Sciences Databases and Information Systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning On Graphs Using Graph Convolutional Networks

Deep Learning On Graphs Using Graph Convolutional Networks

引用

作者： Saurabh Mithe San Jose State University

学位级别：硕士

Graphs are a powerful way to model network data with the objects as nodes and the relationship between the various objects as links. Such graphs contain a plethora of valuable information about the underlying data which can be extracted, analyzed, and visualized using Machine Learning (ML). The challenge to this task is that graphs are non-Euclidean structures which means that they cannot be directly used with ML techniques because ML techniques only work with Euclidean structures like grids or sequences. In order to overcome this challenge, the graph structure first needs to be encoded into an equivalent Euclidean representation in the form of a low-dimensional vector. This low-dimensional vector is called an embedding vector, and the encoding process is called node embedding. Traditionally, user-defined heuristics and matrix- factorization based methods were used for node embedding. However, these methods are slow and perform poorly on large and complex graphs. During the recent years, various ML techniques have been developed that learn the encoding of the graph automatically, and in a faster and more efficient way. A few of these techniques called Graph Convolutional Networks (GCNs) use variants of the convolutional neural networks adapted for graphs, and are implemented using deep neural networks. The aim of this project is two-fold. Firstly, to develop a unified framework focusing on three major GCN techniques in order to analyze, evaluate, and compare their performance on select benchmark datasets for the task of node classification. And secondly, to implement a new aggregator for one of the techniques â GraphSAGE, and compare the performance of the aggregator with the existing GCN methods as well as the other aggregators provided by GraphSAGE.

关键词： Node embedding machine learning graph convolutional net- work node classification. artificial intelligence and robotics Theory and Algorithms

来源：评论

学校读者我要写书评

暂无评论

Assessing Code Obfuscation Of Metamorphic Javascript

Assessing Code Obfuscation Of Metamorphic Javascript

引用

作者： Kaushik Murli San Jose State University

学位级别：硕士

Metamorphic malware is one of the biggest and most ubiquitous threats in the digital world. It can be used to morph the structure of the target code without changing the underlying functionality of the code, thus making it very difficult to detect using signature-based detection and heuristic analysis. The focus of this project is to analyze Metamorphic JavaScript malware and techniques that can be used to mutate the code in JavaScript. To assess the capabilities of the metamorphic engine, we performed experiments to visualize the degree of code morphing. Further, this project discusses potential methods that have been used to detect metamorphic malware and their potential limitations. Based on the experiments performed, SVM has shown promise when it comes to detecting and classifying metamorphic code with a high accuracy. An accuracy of 86% is observed when classifying benign, malware and metamorphic files.

关键词： Metamorphic malware Signature detection Heuristic anal- ysis Support Vector Machines artificial intelligence and robotics Information Security

来源：评论

学校读者我要写书评

暂无评论

Fast High Resolution Image Completion

Fast High Resolution Image Completion

引用

作者： Chinmay Mishra San Jose State University

学位级别：硕士

This paper presents a method for image completion, an active research area in the field of computer vision. The method described in the paper aims at achieving comparable results to other state of the art methods with approximately four and a half times reduction in training time. It is a two step procedure which involves image completion and enhancing the resolution of the completed image. We use the SSIM metric to evaluate the quality of the completed image and to also time our model against other image completion models.

关键词： Generative Adversarial Network Convolution Neural Network Image Completion Image In-painting artificial intelligence and robotics

来源：评论

学校读者我要写书评

暂无评论

On Adversarial Attacks On Deep Learning Models

On Adversarial Attacks On Deep Learning Models

引用

作者： Nag Mani San Jose State University

学位级别：硕士

（Available for download on Friday, May 22, 2020） With recent advancements in the field of artificial intelligence, deep learning has created a niche in the technology space and is being actively used in autonomous and IoT systems globally. Unfortunately, these deep learning models have become susceptible to adversarial attacks which can severely impact their integrity. Research has shown that many state-of-the-art models are vulnerable to attacks by well-crafted adversarial examples. These adversarial examples are perturbed versions of clean data which have small amount of noise added to them. These adversarial samples are imperceptible to the human eye but can easily fool the targeted model. The exposed vulnerabilities of these models raise the question of their usability in safety-critical real-world applications such as autonomous driving and applications in the field of medicine. In this work, I have documented the effectiveness of six different gradient based adversarial attacks on ResNet image recognition model. Defending against these adversaries is a difficult problem and adversarial retraining has been one of the widely used defense technique. Adversarial retraining aims at training a more robust model that is capable of handling the adversarial examples attack proactively. I demonstrate the limitations of the traditional adversarial retraining technique which is effective against some adversaries but fails against more sophisticated attacks. I present a new ensemble defense strategy using adversarial retraining technique which is capable of withstanding six adversarial attacks on cifar10 dataset with accuracy greater than 89.31% and as high as 96.24%.

关键词： image neural net attacks adversarial retraining techniques artificial intelligence and robotics

来源：评论

学校读者我要写书评

暂无评论

Deep Morphological Neural Networks

Deep Morphological Neural Networks

引用

作者： Yucong Shen New Jersey Institute of Technology

学位级别：硕士

Mathematical morphology is a theory and technique applied to collect features like geometric and topological structures in digital images. Determining suitable morphological operations and structuring elements for a give purpose is a cumbersome and time-consuming task. In this paper, morphological neural networks are proposed to address this problem. Serving as a non-linear feature extracting layers in deep learning frameworks, the efficiency of the proposed morphological layer is confirmed analytically and empirically. With a known target, a single-filter morphological layer learns the structuring element correctly, and an adaptive layer can automatically select appropriate morphological operations. For high level applications, the proposed morphological neural networks are tested on several classification datasets which are related to shape or geometric image features, and the experimental results have confirmed the tradeoff between high computational efficiency and high accuracy.

关键词： Deep learning Deep morphological neural network Morphological layer Image morphology artificial intelligence and robotics Other Computer Sciences

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Versus Deep Learning For Malware Detection

Machine Learning Versus Deep Learning For Malware Detection

引用

作者： Parth Jain San Jose State University

学位级别：硕士

It is often claimed that the primary advantage of deep learning is that such models can continue to learn as more data is available, provided that sufficient computing power is available for training. In contrast, for other forms of machine learning it is claimed that models ââsaturate,ââ in the sense that no additional learning can occur beyond some point, regardless of the amount of data or computing power available. In this research, we compare the accuracy of deep learning to other forms of machine learning for malware detection, as a function of the training dataset size. We experiment with a wide variety of hyperparameters for our deep learning models, and we compare these models to results obtained using ï¿½-nearest neighbors. In these experiments, we use a subset of a large and diverse malware dataset that was collected as part of a recent research project.

关键词： machine learning deep learning malware detection artificial intelligence and robotics Information Security

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12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：