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

17 篇 会议

馆藏范围

17 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

16 篇 工学
- 14 篇 计算机科学与技术...
- 3 篇 信息与通信工程
- 3 篇 软件工程
- 2 篇 化学工程与技术
- 2 篇 生物医学工程（可授...
- 1 篇 机械工程
- 1 篇 材料科学与工程（可...
- 1 篇 石油与天然气工程
- 1 篇 生物工程
5 篇 理学
- 4 篇 数学
- 3 篇 生物学
- 2 篇 化学
- 2 篇 系统科学
- 1 篇 物理学
4 篇 管理学
- 4 篇 图书情报与档案管...
1 篇 医学
- 1 篇 基础医学(可授医学...
- 1 篇 临床医学
- 1 篇 药学(可授医学、理...

主题

2 篇 deep learning
2 篇 convolutional ne...
1 篇 multi-label clas...
1 篇 neural architect...
1 篇 interpretability
1 篇 transformer
1 篇 database systems
1 篇 lstm
1 篇 non-parametric e...
1 篇 wear of material...
1 篇 graph edit dista...
1 篇 computational ef...
1 篇 transformers
1 篇 functional conne...
1 篇 handwriting
1 篇 stacking
1 篇 class imbalance
1 篇 primary hyperpar...
1 篇 reach-to-graspin...
1 篇 gray wolf optimi...

机构

3 篇 institute of neu...
2 篇 concordia univ d...
2 篇 univ bologna dep...
2 篇 mila quebec ai i...
1 篇 bory hosp as bra...
1 篇 department of me...
1 篇 ulm univ inst ne...
1 篇 imt scuola alti ...
1 篇 univ siena dipar...
1 篇 faculty of elect...
1 篇 comenius univ de...
1 篇 hop tenon serv m...
1 篇 st elisabeth onc...
1 篇 univ bern inst c...
1 篇 inst natl sci & ...
1 篇 univ siena diism...
1 篇 institute of med...
1 篇 jadavpur univ de...
1 篇 c-com gmbh heink...
1 篇 univ bern inst c...

作者

5 篇 schwenker friedh...
3 篇 riesen kaspar
2 篇 trentin edmondo
2 篇 thiam patrick
2 篇 borra davide
2 篇 bellmann peter
2 篇 ravanelli mirco
1 篇 balogova sona
1 篇 laha sugata
1 篇 betti alessandro
1 篇 meconcelli ducci...
1 篇 kharma nawwaf
1 篇 steinert adrian
1 篇 bandyopadhyay sa...
1 篇 thurnherr hannes
1 篇 casoni michele
1 篇 manzan josé rica...
1 篇 magosso elisa
1 篇 sharma natasha
1 篇 veiga antônio c....

语言

17 篇 英文

检索条件"任意字段=11th IAPR TC3 workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2024"

共 17 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：

11th iapr tc3 workshop on artificial neural networks in pattern recognition, annpr 2024

11th IAPR TC3 workshop on Artificial Neural Networks in Patt...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition, annpr 2024

ISBN: (纸本)9783031716010

the proceedings contain 27 papers. the special focus in this conference is on artificial neural networks in pattern recognition. the topics include: neural Decompiling of Tracr Transformers;pitfalls in Processing Infinite-Length Sequences with Popular Approaches for Sequential Data;robust Clustering with McDonald’s Beta-Liouville Mixture Models for Proportional Data;evaluating Support Vector Machines with Multiple Kernels by Random Search;Automatic Interpretation of 18F-Fluorocholine PET/CT Findings in Patients with Primary Hyperparathyroidism: A Novel Dataset with Benchmarks;a Hybrid Neuroevolutionary Approach to the Design of Convolutional neural networks for 2D and 3D Medical Image Segmentation;An Improved Pix2Pix GAN for Medical Image Generation;vision Transformer Features-Based Leukemia Classification;comparative Study of Deep Learning Models in Melanoma Detection;a Metaheuristic Optimization Based Deep Feature Selection for Oral Cancer Classification;machine Learning for Clinical Score Prediction from Longitudinal Dataset: A Case Study on Parkinson’s Disease;explaining Network Decision Provides Insights on the Causal Interaction Between Brain Regions in a Motor Imagery Task;Multi-modal Decoding of Reach-to-Grasping from EEG and EMG via neural networks;VAeViT: Fusing Multi-views for Complete 3D Object recognition;leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos;palmprint Classification via Filter Faces and Feature Extraction;deep Multi-label Classification of Personality with Handwriting Analysis;license Plate Detection and Character recognition Using Deep Learning and Font Evaluation;experiments in Modeling Disagreement;deep Multiresolution Wavelet Transform for Speech Emotion Assessment of High-Risk Suicide Callers;Dynamic HumTrans: Humming Transcription Using CNNs and Dynamic Programming;Leveraging LSTM Embeddings for River Water Temperature Modeling;research on the Identification of Common Economic Shellfish in Jiang

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Neuroevolutionary Approach to the Design of Convolutional neural networks for 2D and 3D Medical Image Segmentation 11th

A Hybrid Neuroevolutionary Approach to the Design of Convolu...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Ramesh, Nivedha Ashfaq, Tabish Kharma, Nawwaf Concordia Univ Dept Elect & Comp Engn Montreal PQ Canada

ISBN: (纸本)9783031716010;9783031716027

the evolution of Convolutional neural networks (CNNs) has revolutionized medical image segmentation, yet designing optimal architectures remains a challenge. In this paper, we introduce a hybrid evolutionary algorithm that advances the design of CNNs for medical image segmentation. By integrating Cartesian Genetic Programming with Simulated Annealing, our approach efficiently explores the architectural design space, yielding CNN architectures that perform robustly across several medical imaging tasks. Our model demonstrated competitive performance on the DRIVE and Medical Segmentation Decathlon datasets, achieving Dice Similarity Coefficients up to 0.828, and excelling in computational efficiency with reduced GFLOP values. Notably, our algorithm's design eliminates the need for extensive pre-training, reducing computational overhead and enhancing its suitability for resource-constrained environments.

关键词： Medical Image Segmentation Evolutionary Algorithms Computational Efficiency neural Architecture Search (NAS)

来源：评论

学校读者我要写书评

暂无评论

neural Decompiling of Tracr Transformers 11th

Neural Decompiling of Tracr Transformers

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： thurnherr, Hannes Riesen, Kaspar Univ Bern Inst Comp Sci CH-3012 Bern Switzerland

ISBN: (纸本)9783031716010;9783031716027

Recently, the transformer architecture has enabled substantial progress in many areas of pattern recognition and machine learning. However, as with other neural network models, there is currently no general method available to explain their inner workings. the present paper represents a first step towards this direction. We utilize Transformer Compiler for RASP (Tracr) to generate a large dataset of pairs of transformer weights and corresponding RASP programs. Based on this dataset, we then build and train a model, with the aim of recovering the RASP code from the compiled model. We demonstrate that the simple form of Tracr compiled transformer weights is interpretable for such a decompiler model. In an empirical evaluation, our model achieves exact reproductions on more than 30% of the test objects, while the remaining 70% can generally be reproduced with only few errors. Additionally, more than 70% of the programs, produced by our model, are functionally equivalent to the ground truth, and therefore a valid decompilation of the Tracr compiled transformer weights.

关键词： Transformer Interpretability Decompiling RASP

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Matching with Graph neural networks 11th

Learning Graph Matching with Graph Neural Networks

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Dobler, Kalvin Riesen, Kaspar Univ Bern Inst Comp Sci Neubruckstr 10 CH-3012 Bern Switzerland

ISBN: (纸本)9783031716010;9783031716027

Graph matching aims at evaluating the dissimilarity of two graphs by defining a constrained correspondence between their nodes and edges. Error-tolerant graph matching, for instance, introduces the concept of a cost for penalizing structural differences in the matching. A popular method for this approach is graph edit distance, which is based on the cost of the minimal sequence of edit operations to transform a source graph into a target graph. One of the main problems of graph edit distance is the computational complexity, which is exponential in its exact form. In recent years, several approximation methods for graph edit distance have been presented which offer polynomial runtimes. In this paper, we approach the graph edit distance problem in a fundamentally different way. In particular, we propose to learn graph edit distance by means of graph neural networks. In a comprehensive experimental evaluation on six data sets, we verify that our approach not only provides comparable classification performance but also substantially reduces the runtime compared to a prominent algorithm for approximate graph edit distance computation.

关键词： Structural pattern recognition Graph Matching Graph Edit Distance Graph Representation Learning

来源：评论

学校读者我要写书评

暂无评论

Gaussian-Mixture neural networks 11th

Gaussian-Mixture Neural Networks

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Meconcelli, Duccio Trentin, Edmondo Univ Siena DIISM Siena Italy

ISBN: (纸本)9783031716010;9783031716027

Density estimation is crucial to statistical pattern recognition, in both the supervised and unsupervised frameworks. It is still an open problem, due to its intrinsic difficulties and to the many shortcomings of statistical parametric and non-parametric techniques. artificial neural networks (ANN) have long been applied to the estimation of posterior probabilities for pattern classification (a simple supervised learning task), yet only a few attempts have been made to devise ANN-based density estimation algorithms. the paper proposes a novel algorithm for training an ANN from an unlabeled data sample of patterns randomly drawn from an underlying probability density function (PDF), say p(center dot), such that the ANN learns a robust non-parametric model of p(center dot). the algorithm leverages both the generalization capabilities of ANNs and the generality of the maximum-likelihood estimates of the parameters of Gaussian mixture models. therefore, the proposed machine is termed Gaussian-mixture neural Network (GNN). the best selling points of the GNN lie in its simplicity and effectiveness. Preliminary experimental results are reported and analyzed that involve data samples of variable size randomly drawn from PDFs of known form, either unimodal or multimodal. the GNN favorably compares with established statistical and ANN-based estimators, scoring generally higher than its competitors over a range of evaluation metrics. the code used in the experiments is made publicly available online on Github.

关键词： Density estimation Gaussian mixture model artificial neural network non-parametric estimation deep learning

来源：评论

学校读者我要写书评

暂无评论

A Metaheuristic Optimization Based Deep Feature Selection for Oral Cancer Classification 11th

A Metaheuristic Optimization Based Deep Feature Selection fo...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Halder, Akash Laha, Sugata Bandyopadhyay, Saptarshi Schwenker, Friedhelm Sarkar, Ram Jadavpur Univ Dept Comp Sci & Engn Kolkata India Ulm Univ Inst Neural Informat Proc Ulm Germany

ISBN: (纸本)9783031716010;9783031716027

Oral cancer is a serious hazard to world health, with many new cases recorded each year. Researchers have been concentrating on developing medical image analysis-based computer-aided diagnostic (CAD) systems for oral cancer. To this end, we propose a novel model that we name GrayWolf Optimization (GWO) based deep Feature Selection Network (GFS-Net). Initially, we use an attention-aided NASNet Mobile, a convolutional neural network (CNN) architecture, to extract features from the input images. Next, we use a metaheuristic-based optimization algorithm, called GWO, to get rid of the extraneous features obtained from the CNN model. For the final classification task, the K-Nearest-Neighbours (KNN) classifier is applied with this optimal feature set. Our model is evaluated on two publicly accessible oral cancer datasets, histopathologic oral cancer identification dataset and oral cancer (lips and tongue) dataset, that yields classification accuracies of 92.86% and 93.94%, respectively. the code and additional results are available at https://***/stellarsb7/GFS-Net.

关键词： Oral Cancer Deep Learning Feature Selection Gray Wolf Optimization Attention Mechanism Medical Image

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-label Classification of Personality with Handwriting Analysis 11th

Deep Multi-label Classification of Personality with Handwrit...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Shamsabad, Marzieh Adeli Suen, Ching Yee Concordia Univ Ctr Pattern Recognit & Machine Intelligence CENPA Montreal PQ H3G 1M8 Canada

ISBN: (纸本)9783031716010;9783031716027

Handwriting analysis has traditionally been used to infer personality traits from the stylistic features of writing. With advances in machine learning, the accuracy and applicability of these analyses have significantly improved. this paper presents a new multi-label classification approach to classify personality traits, such as Extraversion and Conscientiousness, into Low, Average, and High categories. this approach uses Binary Cross-Entropy with Logits Loss and Focal Loss to handle multi-label classification and class imbalance. Image segmentation techniques are also employed to enhance the handling of limited handwriting samples. the paper evaluates the complexity and performance of ResNet-50 and ResNet-101 architectures in recognizing complex handwriting patterns using three optimizers: SGD with momentum, Adam, and AdaBelief. the results demonstrate the efficacy of our proposed method, improving overall accuracy from 67.09% to 90.16% for ResNet-50 and from 69.43% to 90.07% for ResNet-101, with an overall AUC of 0.96. these improvements emphasize the model's capability for practical automated handwriting analysis.

关键词： Handwriting Multi-label classification Class Imbalance Binary Cross-Entropy with Logits Loss Focal Loss

来源：评论

学校读者我要写书评

暂无评论

Leveraging LSTM Embeddings for River Water Temperature Modeling 11th

Leveraging LSTM Embeddings for River Water Temperature Model...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Fankhauser, Benjamin Bigler, Vidushi Riesen, Kaspar Univ Bern Inst Comp Sci Bern Switzerland Bern Univ Appl Sci Inst Optimisat & Data Anal Biel Switzerland

ISBN: (纸本)9783031716010;9783031716027

River water temperature modeling is a major task in climate research. State-of-the-art methods for water temperature modeling deploy a transductive design, which makes it difficult to generalize to unseen water stations during test time. In the present paper, we isolate one of the common building blocks - a central LSTM, trained for each water station - and propose an embedding scheme in order to increase both the prediction accuracy and the amount of shared parameters and thus the generalization. the proposed embeddings are learned during training time. In an empirical evaluation we show that our method is able to reduce the RMSE by about five percentage points compared to the state-of-the-art reference method while decreasing the tuneable parameters by several orders of magnitude. We also provide a sample analysis of the embedding space of the catchment area of one specific river. Looking at the results of this qualitative analysis, we come to the conclusion that deploying an embedding in water temperature models is not only convincing to decrease the RMSE of water temperature predictions, but also enables better explainable deep learning models. Moreover, the proposed embedding technique opens up various unexplored applications in water temperature research.

关键词： Water Temperature Embedding LSTM Recurrent neural Network

来源：评论

学校读者我要写书评

暂无评论

Pitfalls in Processing Infinite-Length Sequences with Popular Approaches for Sequential Data 11th

Pitfalls in Processing Infinite-Length Sequences with Popula...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Casoni, Michele Guidi, Tommaso Tiezzi, Matteo Betti, Alessandro Gori, Marco Melacci, Stefano Univ Siena DIISM I-52100 Siena Italy IMT Scuola Alti Studi I-55100 Lucca Italy

ISBN: (纸本)9783031716010;9783031716027

One of the enduring challenges for the Machine Learning community is developing models that can process and learn from very long data sequences. Transformer-based models and Recurrent neural networks (RNNs) have excelled in processing long sequences, yet face challenges in transitioning to processing infinite-length sequences online, a crucial step in mimicking human learning over continuous data streams. While Transformer models handle large context windows efficiently, they suffer from quadratic computational costs, motivating research into alternative attention mechanisms. Conversely, RNNs, particularly Deep State-Space Models (SSMs), have shown promise in long sequence tasks, outperforming Transformers in certain benchmarks. However, current approaches are limited to finite-length sequences, which are pre-buffered and randomly shuffled to cope with stochastic gradient descent. this paper addresses the fundamental gap in transitioning from offline-processing of a dataset of sequences to online-processing of possibly infinite-length sequences, a scenario often neglected in existing research. Empirical evidence is presented, demonstrating the performance and limits of existing models. We highlight the challenges and opportunities in learning from a continuous data stream, paving the way for future research in this area.

关键词： Recurrent neural networks Transformers Long Sequences Online Learning Learning over Time

来源：评论

学校读者我要写书评

暂无评论

Explaining Network Decision Provides Insights on the Causal Interaction Between Brain Regions in a Motor Imagery Task 11th

Explaining Network Decision Provides Insights on the Causal ...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Borra, Davide Ravanelli, Mirco Univ Bologna Dept Elect Elect & Informat Engn Guglielmo Marcon Cesena Campus Cesena Italy Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada Mila Quebec AI Inst Montreal PQ Canada

ISBN: (纸本)9783031716010;9783031716027

neural decoding widely exploits machine learning for classifying electroencephalographic (EEG) signals for brain-computer interface applications. Recent advancements in neural decoding regards the use of brain functional connectivity estimates as input features and the adoption of convolutional neural networks (CNNs) to realize decoders. Moreover, explainable artificial intelligence (XAI) approaches based on CNNs are growing interest in the neuroscience community, for validating the knowledge learned by networks and for using the decoder not only to classify the EEG but also to analyze it in a data-driven way, without a priori assumptions. However, the adoption of connectivity estimates for neural decoding is still in its infancy, as adopts non-directed connectivity measures, limits the analysis of few interactions/frequency ranges, and exploits classic machine learning approaches without exploring CNNs. Moreover, XAI approaches have never been applied to analyze EEG-based functional connectivity. To overcome these limitations, we design and apply a CNN for processing directed connectivity measures estimated via spectral Granger causality. the CNN automatically learns features in the frequency and spatial domains, and it is coupled with an explanation technique (DeepLIFT) for highlighting the most relevant connectivity inflow and outflow associated to each decoded brain state. Our approach is applied to motor imagery decoding, and achieves state-of-the-art performance compared to existing networks. DeepLIFT relevance representations match the directional interactions known occurring when imagining movements, validating the features related to the brain network, as learned by the CNN.

关键词： Electroencephalogram Functional connectivity Convolutional neural networks Explainable AI Motor imagery

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2页 << < 1 2 > >>

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：