检索结果-内蒙古大学图书馆

A distributed neural system for top-down face processing

Neuroscience Letters 2009年第1期451卷 6-10页

作者： Li, Jun Liu, Jiangang Liang, Jimin Zhang, Hongchuan Zhao, Jizheng Huber, David E. Rieth, Cory A. Lee, Kang Tian, Jie Shi, Guangming Life Science Research Center School of Electronic Engineering Xidian University Xi'an Shaanxi 710071 China School of Computer and Information Technology Beijing Jiaotong University Beijing 1000441 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China Developmental Cognitive Neuroscience Laboratory Northwestern University IL United States Department of Psychology University of California San Diego La Jolla CA United States Institute of Child Study University of Toronto Toronto Ont. Canada

Evidence suggests that the neural system associated with face processing is a distributed cortical network containing both bottom-up and top-down mechanisms. While bottom-up face processing has been the focus of many studies, the neural areas involved in the top-down face processing have not been extensively investigated due to difficulty in isolating top-down influences from the bottom-up response engendered by presentation of a face. In the present study, we used a novel experimental method to induce illusory face-detection. This method allowed for directly examining the neural systems involved in top-down face processing while minimizing the influence of bottom-up perceptual input. A distributed cortical network of top-down face processing was identified by analyzing the functional connectivity patterns of the right fusiform face area (FFA). This distributed cortical network model for face processing includes both "core" and "extended" face processing areas. It also includes left anterior cingulate cortex (ACC), bilateral orbitofrontal cortex (OFC), left dorsolateral prefrontal cortex (DLPFC), left premotor cortex, and left inferior parietal cortex. These findings suggest that top-down face processing contains not only regions for analyzing the visual appearance of faces, but also those involved in processing low spatial frequency (LSF) information, decision-making, and working memory. © 2008 Elsevier Ireland Ltd.

关键词： Distributed cortical network Face processing fMRI Psychophysiological interaction (PPI) Top-down processing

来源：评论

学校读者我要写书评

暂无评论

Deep Kernel Embedded Clustering Network

SSRN

引用

SSRN 2024年

作者： Ren, Lina Huang, Ruizhang Chen, Yanping Lin, Chuan Qin, Yongbin State Key Laboratory of Public Big Data Text Computing and Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and Technology Guizhou University Guiyang550025 China Department of Information Engineering Guizhou Light Industry Technical College Guiyang550025 China

In this paper, we propose a deep kernel embedded clustering network, namely DKEC, which learns data partitions with kernelized semantic embeddings of data samples via a self-supervised deep neural network. A kernelized semantic embedding learner is designed to learn high quality data representations, which not only capture the data semantic characteristics but also show good structural separable characteristics. Other than directly apply traditional predefined kernel mapping methods, the kernelized semantic embedding learner, investigated by a deep variational Gaussian process, is able to learn the kernel mapping according to the nature of various datasets automatically, while maintain reasonable computational complexity. The DKEC, which is an end-to-end deep clustering network, is invested based on the kernelized semantic embedding learner. A triplet self-supervised optimization objective is designed in the DKEC model to guide the clustering partition, the separable factor of the kernelized semantic embedding, and the data reconstruction factor of the kernelized semantic embedding, simultaneously. We conducted extensive experiments on $ 7 $ real-world datasets. The results unequivocally showcase the exceptional clustering performance of the proposed DKEC. © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Reference language based unsupervised neural machine translation

arXiv

引用

arXiv 2020年

作者： Li, Zuchao Zhao, Hai Wang, Rui Utiyama, Masao Sumita, Eiichiro Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Kyoto Japan

Exploiting common language as an auxiliary for better translation has a long tradition in machine translation, which lets supervised learning based machine translation enjoy the enhancement delivered by the well-used pivot language, in case that the prerequisite of parallel corpus from source language to target language cannot be fully satisfied. The rising of unsupervised neural machine translation (UNMT) seems completely relieving the parallel corpus curse, though still subject to unsatisfactory performance so far due to vague clues available used for its core back-translation training. Further enriching the idea of pivot translation by freeing the use of parallel corpus other than its specified source and target, we propose a new reference language based UNMT framework, in which the reference language only shares parallel corpus with the source, indicating clear enough signal to help the reconstruction training of UNMT through a proposed reference agreement mechanism. Experimental results show that our methods improve the quality of UNMT over that of a strong baseline in terms of only one auxiliary language, demonstrating the usefulness of the proposed reference language based UNMT with a good start. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

A statistical learning method for identification of analysis classes from requirements in korean

International Journal of Multimedia and Ubiquitous Engineeri...

引用

International Journal of Multimedia and Ubiquitous engineering 2013年第1期8卷 255-264页

作者： Jeong, Hyoungil Seo, Jungyun Park, Soojin Department of Computer Science and Engineering Sogang University 121-742 Korea Republic of Interdisciplinary Program of Integrated Biotechnology Sogang University 121-742 Korea Republic of Sogang Institute of Advanced Technology Sogang University 121-742 Korea Republic of

Identification of analysis classes is a critical design decision to be made early in the design phase in software development. Although incorrect identification of analysis classes can diminish the quality of a whole software design, it still heavily relies on the expertise and experience of the developer and has been ad-hoc. The majority existing works on identification of analysis classes focus on the rule-based approaches. However, the rule-based approaches which are used for analyzing sentence structures cannot be adopted for the language, which has very flexible word order like Korean. In this paper, we proposed a statistical learning method for identification of analysis classes from requirements sentences in Korean. The approach is evaluated using the precision and recall of the automatically extracted candidate classes from real requirements sentences in Korean. The result shows that we can promise numerically measurable enhancement of performance on solving the automatic identification problem of analysis classes using statistical methods, in the real use case specifications of a banking system.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Unsupervised full constituency parsing with neighboring distribution divergence

arXiv

引用

arXiv 2021年

作者： Peng, Letian Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Unsupervised constituency parsing has been explored much but is still far from being solved. Conventional unsupervised constituency parser is only able to capture the unlabeled structure of sentences. Towards unsupervised full constituency parsing, we propose an unsupervised and training-free labeling procedure by exploiting the property of a recently introduced metric, Neighboring Distribution Divergence (NDD), which evaluates semantic similarity between sentences before and after editions. For implementation, we develop NDD into Dual POS-NDD (DP-NDD) and build "molds" to detect constituents and their labels in sentences. We show that DP-NDD not only labels constituents precisely but also inducts more accurate unlabeled constituency trees than all previous unsupervised methods with simpler rules. With two frameworks for labeled constituency trees inference, we set both the new state-of-the-art for unlabeled F1 and strong baselines for labeled F1. In contrast with the conventional predicting- and-evaluating scenario, our method acts as an plausible example to inversely apply evaluating metrics for prediction. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Hierarchical contextualized representation for named entity recognition

arXiv

引用

arXiv 2019年

作者： Luo, Ying Xiao, Fengshun Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from larger scope, not only in the entire sentence, but also in the entire document (dataset). In this paper, we address these two deficiencies and propose a model augmented with hierarchical contextualized representation: Sentence-level representation and document-level representation. In sentencelevel, we take different contributions of words in a single sentence into consideration to enhance the sentence representation learned from an independent BiLSTM via label embedding attention mechanism. In document-level, the key-value memory network is adopted to record the document-aware information for each unique word which is sensitive to similarity of context information. Our two-level hierarchical contextualized representations are fused with each input token embedding and corresponding hidden state of BiLSTM, respectively. The experimental results on three benchmark NER datasets (CoNLL-2003 and Ontonotes 5.0 English datasets, CoNLL-2002 Spanish dataset) show that we establish new state-of-the-art results. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Bipartite Flat-Graph Network for Nested Named Entity Recognition

arXiv

引用

arXiv 2020年

作者： Luo, Ying Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

In this paper, we propose a novel bipartite flat-graph network (BiFlaG) for nested named entity recognition (NER), which contains two subgraph modules: a flat NER module for outermost entities and a graph module for all the entities located in inner layers. Bidirectional LSTM (BiLSTM) and graph convolutional network (GCN) are adopted to jointly learn flat entities and their inner dependencies. Different from previous models, which only consider the unidirectional delivery of information from innermost layers to outer ones (or outside-to-inside), our model effectively captures the bidirectional interaction between them. We first use the entities recognized by the flat NER module to construct an entity graph, which is fed to the next graph module. The richer representation learned from graph module carries the dependencies of inner entities and can be exploited to improve outermost entity predictions. Experimental results on three standard nested NER datasets demonstrate that our BiFlaG outperforms previous state-of-the-art models. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Topic-aware multi-turn dialogue modeling

arXiv

引用

arXiv 2020年

作者： Xu, Yi Zhao, Hai Zhang, Zhuosheng Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances. As a conversation goes on, topic shift at discourse-level naturally happens through the continuous multi-turn dialogue context. However, all known retrieval-based systems are satisfied with exploiting local topic words for context utterance representation but fail to capture such essential global topic-aware clues at discourse-level. Instead of taking topic-agnostic ngram utterance as processing unit for matching purpose in existing systems, this paper presents a novel topic-aware solution for multi-turn dialogue modeling, which segments and extracts topic-aware utterances in an unsupervised way, so that the resulted model is capable of capturing salient topic shift at discourse-level in need and thus effectively track topic flow during multi-turn conversation. Our topic-aware modeling is implemented by a newly proposed unsupervised topic-aware segmentation algorithm and Topic-Aware Dual-attention Matching (TADAM) Network, which matches each topic segment with the response in a dual cross-attention way. Experimental results on three public datasets show TADAM can outperform the state-of-the-art method by a large margin, especially by 3.4% on E-commerce dataset that has an obvious topic shift. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

FINE-TUNING TRANSFER LEARNING MODEL IN WOVEN FABRIC PATTERN CLASSIFICATION

引用

International Journal of Innovative Computing, Information and Control 2022年第6期18卷 1885-1894页

作者： Noprisson, Handrie Ermatita, Ermatita Abdiansah, Abdiansah Ayumi, Vina Purba, Mariana Setiawan, Hadiguna Program of Doctoral Program in Engineering Universitas Sriwijaya Jalan Raya Prabumulih-Inderalaya Palembang30128 Indonesia Faculty of Computer Science Universitas Sriwijaya Jalan Raya Prabumulih-Inderalaya Palembang30128 Indonesia Department of Research and Development Stikhafi Academy Jalan Timur Indah Raya Bengkulu38225 Indonesia

It is important to figure out the patterns of woven fabrics before producing woven fabric with a machine. Recognition of woven fabric pattern usually with the help of the human eye can understand the fabric pattern. However, this manual checking takes a lot of time, money, and work, which will raise the cost of making woven fabrics. This study uses the VGG16, VGG19, MobileNet, and Inception-V3 methods to classify woven fabric patterns. It also wants to see how fine-tuning method can help algorithms be more accurate at classifying images. The research was divided into four phases, including image acquisition, image preprocessing, image classification and evaluation. A total of 978 pictures of motifs included in the research dataset. There are 351 images for the cotton class, 76 images for linen, 195 images for silk, and 356 images for wool. As the result, the highest testing accuracy was in the Inception-V3 experiment (with fine-tuning) of 72.51%, and the lowest was in the VGG19 experiment (with fine-tuning) of 52.92%. © 2022 ICIC International.

关键词： Weaving

来源：评论

学校读者我要写书评

暂无评论

SAUCE: Synchronous and Asynchronous User-Customizable Environment for Multi-Agent LLM Interaction

arXiv

引用

arXiv 2024年

作者： Neuberger, Shlomo Eckhaus, Niv Berger, Uri Taubenfeld, Amir Stanovsky, Gabriel Goldstein, Ariel The Hebrew University Business School Jerusalem Israel School of Computer Science and Engineering The Hebrew University of Jerusalem School of Computing and Information Systems University of Melbourne Australia Department of Cognitive and Brain Sciences The Hebrew University of Jerusalem Israel Google Research United States

Many human interactions, such as political debates, are carried out in group settings, where there are arbitrarily many participants, each with different views and agendas. To explore such complex social settings, we present SAUCE: a customizable Python platform, allowing researchers to plug-and-play various LLMs participating in discussions on any topic chosen by the user. Our platform takes care of instantiating the models, scheduling their responses, managing the discussion history, and producing a comprehensive output log, all customizable through configuration files, requiring little to no coding skills. A novel feature of SAUCE is our asynchronous communication feature, where models decide when to speak in addition to what to say, thus modeling an important facet of human communication. We show SAUCE’s attractiveness in two initial experiments, and invite the community to use it in simulating various group simulations. © 2024, CC BY.

关键词： Chatbots

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：