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

68 篇 会议
13 篇 期刊文献

馆藏范围

81 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

76 篇 工学
- 74 篇 计算机科学与技术...
- 13 篇 软件工程
- 5 篇 信息与通信工程
- 4 篇 生物工程
- 2 篇 化学工程与技术
- 2 篇 生物医学工程（可授...
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 控制科学与工程
- 1 篇 土木工程
16 篇 理学
- 11 篇 数学
- 8 篇 生物学
- 3 篇 系统科学
- 2 篇 物理学
- 2 篇 化学
- 1 篇 地球物理学
- 1 篇 地质学
- 1 篇 统计学（可授理学、...
6 篇 管理学
- 5 篇 图书情报与档案管...
- 1 篇 管理科学与工程(可...
3 篇 法学
- 3 篇 社会学
2 篇 医学
- 2 篇 基础医学(可授医学...
- 2 篇 临床医学
- 2 篇 药学(可授医学、理...

主题

5 篇 supervised learn...
4 篇 recursive neural...
3 篇 deep learning
3 篇 neural networks
3 篇 face recognition
3 篇 pattern recognit...
3 篇 feature extracti...
2 篇 vision transform...
2 篇 multi-label clas...
2 篇 mixture modeling
2 篇 weighting of dat...
2 篇 semiconductor ma...
2 篇 pattern classifi...
2 篇 human computer i...
2 篇 graph edit dista...
2 篇 feed-forward neu...
2 篇 polynomial appro...
2 篇 class imbalance
2 篇 learning prefere...
2 篇 time series fore...

机构

5 篇 concordia univ d...
4 篇 univ ulm inst ne...
3 篇 univ jaume 1 dep...
2 篇 univ london birk...
2 篇 institute of neu...
2 篇 multimedia univ ...
2 篇 institute for in...
2 篇 helsinki univ te...
2 篇 institute of neu...
2 篇 univ paris 06 la...
2 篇 univ hosp ulm de...
2 篇 ctr pattern regc...
2 篇 concordia univ d...
2 篇 univ toulouse 3 ...
2 篇 univ patras upai...
2 篇 univ ulm dept ne...
2 篇 institute of com...
2 篇 univ catholique ...
2 篇 univ siena dipar...
2 篇 ucl dept comp sc...

作者

12 篇 schwenker friedh...
5 篇 trentin edmondo
5 篇 hernandez-espino...
5 篇 fernandez-redond...
5 篇 torres-sospedra ...
4 篇 riesen kaspar
4 篇 palm guenther
4 篇 kestler hans a.
3 篇 krzyzak adam
3 篇 scherer stefan
2 篇 granger eric
2 篇 piccinini f
2 篇 pudil p
2 篇 frasconi p
2 篇 ziou d
2 篇 simon g
2 篇 inesta jm
2 篇 krzyzak a
2 篇 brown m
2 篇 michel-sendis c

语言

81 篇 英文

检索条件"任意字段=1st IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition"

共 81 条记录，以下是11-20 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：

Introducing an Atypical Loss: A Perceptual Metric Learning for Image Pairing 10th

Introducing an Atypical Loss: A Perceptual Metric Learning f...

引用

10th iapr tc3 workshop on artificial neural networks for pattern recognition (ANNPR)

作者： Dahmane, Mohamed CRIM Comp Res Inst Montreal Montreal PQ H3N 1M3 Canada

ISBN: (纸本)9783031206498;9783031206504

Recent works have shown an interest in comparing visually similar but semantically different instances. The paired Totally Looks Like (TLL) image dataset is a good example of visually similar paired images to figure out how humans compare images. In this research, we consider these more generic annotated categories to build a semantic manifold distance. We introduce an atypical triplet-loss using the inverse Kullback-Leibler divergence to model the distribution of the anchor-positive (a-p) distances. In the new redefinition of triplet-loss, the anchor-negative (a-n) loss is conditional to the a-p distance distribution which prevents the loss correction fluctuations in the plain summed triplet-loss function of absolute distances. The proposed atypical triplet-loss builds a manifold from relative distances to a "super" anchor represented by the a-p distribution. The evaluation on the paired images of the TLL dataset showed that the retrieving score from the first candidate guess (top-1) is 75% which is x 2.5 higher compared to the recall score of the baseline triplet-loss which is limited to 29%, and with a top-5 pairing score as high as 78% which represents a gain of x1.4.

关键词： Atypical loss Metric learning Visual relationship Image pairing Image perception Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Typing plasmids with distributed sequence representation 9th

Typing plasmids with distributed sequence representation

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, ANNPR 2020

作者： Kaufmann, Moritz Schüle, Martin Smits, Theo H. M. Pothier, Joël F. Einsiedlerstr. 31 Wädenswil8820 Switzerland Schloss 1 Wädenswil8820 Switzerland

ISBN: (纸本)9783030583088

Multidrug resistant bacteria represent an increasing challenge for medicine. In bacteria, most antibiotic resistances are transmitted by plasmids. Therefore, it is important to study the spread of plasmids in detail in order to initiate possible countermeasures. The classification of plasmids can provide insights into the epidemiology and transmission of plasmid-mediated antibiotic resistance. The previous methods to classify plasmids are replicon typing and MOB typing. Both methods are time consuming and labor-intensive. Therefore, a new approach to plasmid typing was developed, which uses word embeddings and support vector machines (SVM) to simplify plasmid typing. Visualizing the word embeddings with t-distributed stochastic neighbor embedding (t-SNE) shows that the word embeddings finds distinct structure in the plasmid sequences. The SVM assigned the plasmids in the testing dataset with an average accuracy of 85.9% to the correct MOB type. © Springer Nature Switzerland AG 2020.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Using cnns to optimize numerical simulations in geotechnical engineering 9th

Using cnns to optimize numerical simulations in geotechnical...

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, ANNPR 2020

作者： Wolf, Beat Donzallaz, Jonathan Jost, Colette Hayoz, Amanda Commend, stéphane Hennebert, Jean Kuonen, Pierre iCoSys University of Applied Sciences Western Switzerland Fribourg Switzerland iTEC University of Applied Sciences Western Switzerland Fribourg Switzerland

ISBN: (纸本)9783030583088

Deep excavations are today mainly designed by manually optimising the wall’s geometry, stiffness and strut or anchor layout. In order to better automate this process for sustained excavations, we are exploring the possibility of approximating key values using a machine learning (ML) model instead of calculating them with time-consuming numerical simulations. After demonstrating in our previous work that this approach works for simple use cases, we show in this paper that this method can be enhanced to adapt to complex real-world supported excavations. We have improved our ML model compared to our previous work by using a convolutional neural network (CNN) model, coding the excavation configuration as a set of layers of fixed height containing the soil parameters as well as the geometry of the walls and struts. The system is trained and evaluated on a set of synthetically generated situations using numerical simulation software. To validate this approach, we also compare our results to a set of 15 real-world situations in a t-SNE. Using our improved CNN model we could show that applying machine learning to predict the output of numerical simulation in the domain of geotechnical engineering not only works in simple cases but also in more complex, real-world situations. © Springer Nature Switzerland AG 2020.

关键词： Excavation

来源：评论

学校读者我要写书评

暂无评论

Feature extraction: A time window analysis based on the x-ite pain database 9th

Feature extraction: A time window analysis based on the x-it...

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, ANNPR 2020

作者： Ricken, Tobias steinert, Adrian Bellmann, Peter Walter, steffen Schwenker, Friedhelm Institute of Neural Information Processing Ulm University James-Franck-Ring Ulm89081 Germany Department of Medical Psychology Ulm University Frauensteige 6 Ulm89075 Germany

ISBN: (纸本)9783030583088

In this work, we analyse different temporal feature extraction window approaches, in combination with short-time heat and electric pain stimuli. Thereby, we focus on the physiological signals of the Experimentally Induced Thermal and Electrical (X-ITE) Pain Database. Each of our proposed approaches is evaluated based on the leave-one-subject-out cross-validation using the random forest method. Moreover, the effectiveness of each physiological signal is inspected separately, as well as by applying the feature fusion approach. Thereby, we analyse different binary classification tasks, as well as four-class classification tasks. Our outcomes indicate that a shifted temporal feature extraction window increases the classification performance significantly, when pain is induced by thermal stimuli. Moreover, our evaluations point out that the outcomes differ significantly, when participants are exposed to electrical pain stimuli. For short-term electric pain stimuli, the best results are obtained without temporal shifts of the feature extraction windows. © Springer Nature Switzerland AG 2020.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Pain intensity recognition - an analysis of short-time sequences in a real-world scenario 9th

Pain intensity recognition - an analysis of short-time seque...

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, ANNPR 2020

作者： Bellmann, Peter Thiam, Patrick Schwenker, Friedhelm Institute of Neural Information Processing Ulm University James-Franck-Ring Ulm89081 Germany Institute of Medical Systems Biology Ulm University Albert-Einstein-Allee 11 Ulm89081 Germany

ISBN: (纸本)9783030583088

Pain intensity recognition still constitutes a challenging classification task. In this work, we focus on the physiological signals of the publicly available BioVid Heat Pain Database, which was collected at Ulm University. The BioVid Heat Pain Database consists of different recordings of healthy test subjects that were exposed to various short-time heat stimuli. The results reported in the literature, which are based on those short-time sequences do not justify the implementation of automated pain detection systems, due to unsatisfactory accuracy rates. In the current study, we show that the outcomes, which are stated in the literature, most likely represent lower bound estimations. For this purpose, we transfer the classification task, which is provided by the BioVid Heat Pain Database, to a real-world scenario. More precise, according to an expected hospital setting, we analyse the automated pain intensity recognition approach in combination with different sets of short-time sequences. Our outcomes indicate, that in real-world applications, where the detection of pain intensity is based on more than one single short-time sequence, the accuracy values can be significantly improved. In the current study, the classification performance of bagged decision tree ensembles is evaluated, based on a person-independent scenario. © Springer Nature Switzerland AG 2020.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A Refinement Algorithm for Deep Learning via Error-Driven Propagation of Target Outputs 8th

A Refinement Algorithm for Deep Learning via Error-Driven Pr...

引用

8th iapr tc3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Laveglia, Vincenzo Trentin, Edmondo Univ Firenze DINFO Via S Marta 3 I-50139 Florence Italy Univ Siena DIISM Via Roma 56 I-53100 Siena Italy

ISBN: (纸本)9783319999784;9783319999777

Target propagation in deep neural networks aims at improving the learning process by determining target outputs for the hidden layers of the network. To date, this has been accomplished via gradient-descent or relying on autoassociative networks applied top-to-bottom in order to synthesize targets at any given layer from the targets available at the adjacent upper layer. This paper proposes a different, error-driven approach, where a regular feed-forward neural net is trained to estimate the relation between the targets at layer l and those at layer l - 1 given the error observed at layer l. The resulting algorithm is then combined with a pre-training phase based on backpropagation, realizing a proficuous "refinement" strategy. Results on the MNIst database validate the feasibility of the approach.

关键词： Target propagation Deep learning Deep neural network Refinement learning

来源：评论

学校读者我要写书评

暂无评论

Manifold Learning Regression with Non-stationary Kernels 8th

Manifold Learning Regression with Non-stationary Kernels

引用

8th iapr tc3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Kuleshov, Alexander Bernstein, Alexander Burnaev, Evgeny Skolkovo Inst Sci & Technol Skolkovo Innovat Ctr 3 Nobel St Moscow 121205 Russia

ISBN: (纸本)9783319999784;9783319999777

Nonlinear multi-output regression problem is to construct a predictive function which estimates an unknown smooth mapping from q-dimensional inputs to m-dimensional outputs based on a training data set consisting of given "input-output" pairs. In order to solve this problem, regression models based on stationary kernels are often used. However, such approaches are not efficient for functions with strongly varying gradients. There exist some attempts to introduce non-stationary kernels to account for possible non-regularities, although even the most efficient one called Manifold Learning Regression (MLR), which estimates the unknown function as well its Jacobian matrix, is too computationally expensive. The main problem is that the MLR is based on a computationally intensive manifold learning technique. In this paper we propose a modified version of the MLR with significantly less computational complexity while preserving its accuracy.

关键词： Nonlinear multi-output regression Manifold learning regression Non-stationary kernel

来源：评论

学校读者我要写书评

暂无评论

Learning neural Models for End-to-End Clustering 8th

Learning Neural Models for End-to-End Clustering

引用

8th iapr tc3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Meier, Benjamin Bruno Elezi, Ismail Amirian, Mohammadreza Duerr, Oliver stadelmann, Thilo ZHAW Datalab Winterthur Switzerland Sch Engn Winterthur Switzerland ARGUS DATA INSIGHTS Schweiz AG Zurich Switzerland Ca Foscari Univ Venice Venice Italy Ulm Univ Inst Neural Informat Proc Ulm Germany HTWG Konstanz Inst Opt Syst Constance Germany

ISBN: (纸本)9783319999784;9783319999777

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1 <= k <= k(max), a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/ different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this "learning to cluster" and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.

关键词： Perceptual grouping Learning to cluster Speech & image clustering

来源：评论

学校读者我要写书评

暂无评论

F-Measure Curves for Visualizing Classifier Performance with Imbalanced Data 8th

F-Measure Curves for Visualizing Classifier Performance with...

引用

8th iapr tc3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Soleymani, Roghayeh Granger, Eric Fumera, Giorgio Univ Quebec Ecole Technol Super Lab Imagerie Vis & Intelligence Artificielle Montreal PQ Canada Univ Cagliari Dept Elect & Elect Engn Pattern Recognit & Applicat Lab Cagliari Italy

ISBN: (纸本)9783319999784;9783319999777

Training classifiers using imbalanced data is a challenging problem in many real-world recognition applications due in part to the bias in performance that occur for: (1) classifiers that are often optimized and compared using unsuitable performance measurements for imbalance problems;(2) classifiers that are trained and tested on a fixed imbalance level of data, which may differ from operational scenarios;(3) cases where the preference of correct classification of classes is application dependent. Specialized performance evaluation metrics and tools are needed for problems that involve class imbalance, including scalar metrics that assume a given operating condition (skew level and relative preference of classes), and global evaluation curves or metrics that consider a range of operating conditions. We propose a global evaluation space for the scalar F-measure metric that is analogous to the cost curves for expected cost. In this space, a classifier is represented as a curve that shows its performance over all of its decision thresholds and a range of imbalance levels for the desired preference of true positive rate to precision. Experiments with synthetic data show the benefits of evaluating and comparing classifiers under different operating conditions in the proposed F-measure space over ROC, precision-recall, and cost spaces.

关键词： Class imbalance Performance visualization tools F-measure

来源：评论

学校读者我要写书评

暂无评论

Time Series Classification in Reservoir-and Model-Space: A Comparison 7th

Time Series Classification in Reservoir-and Model-Space: A C...

引用

7th iapr tc3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Aswolinskiy, Witali Reinhart, Rene Felix steil, Jochen Res Inst Cognit & Robot CoR Lab Univ Str 25 D-33615 Bielefeld Germany Fraunhofer Res Inst Mech Syst Design IEM Zukunftsmeile 1 D-33102 Paderborn Germany

ISBN: (纸本)9783319461823;9783319461816

Learning in the space of Echo state Network (ESN) output weights, i.e. model space, has achieved excellent results in time series classification, visualization and modelling. This work presents a systematic comparison of time series classification in the model space and the classical, discriminative approach with ESNs. We evaluate the approaches on 43 univariate and 18 multivariate time series. It turns out that classification in the model space achieves often better classification rates, especially for high-dimensional motion datasets.

关键词： Time series classification Echo state Network Model space

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9页 << < 1 2 3 4 5 6 7 8 9 > >>

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：