检索结果-内蒙古大学图书馆

Chaining and historical adjective extension 42

Chaining and historical adjective extension

42nd Annual Meeting of the cognitive science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： Grewal, Karan Xu, Yang Department of Computer Science University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

A hallmark of natural language is the innovative reuse of existing words. We examine how adjectives extend over time to describe nouns and form previously unattested adjective-noun pairings. Our approach is based on the idea of chaining that postulates word meaning to extend by linking novel referents to existing ones that are close in semantic space. We test this proposal by exploring a set of models that learn to infer adjective-noun pairings from historical text corpora for a period of 150 years. Our findings across three diverse sets of adjectives support a chaining mechanism that is sensitive to semantic neighbourhood density, best captured by an exemplar model of category extension. This work sheds light on the generative cognitive mechanisms of word usage extension. © 2020 The Author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Infinite mixture chaining: Efficient temporal construction of word meaning 44

Infinite mixture chaining: Efficient temporal construction o...

引用

44th Annual Meeting of the cognitive science Society: cognitive Diversity, CogSci 2022

作者： Yu, Lei Xu, Yang Department of Computer Science University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

Word meanings extend over time due to a functional need for maintaining communicative expressivity within a compact lexicon. Previous scholars have suggested that word meanings extend via a process of chaining, whereby novel items link to existing ones close in semantic space. Recent work has formalized this idea using computational models grounded typically in the exemplar and prototype theories of categorization that are either memory-intensive or simplistic in representation. We propose an alternative account of chaining that optimizes cognitive efficiency by trading off representational accuracy with memory complexity. We operationalize this efficient chaining as an infinite mixture model and show how it constructs the internal representations of word meaning adaptively through time while predicting the historical development of English verb meanings with precision and limited resources. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Children's overextension as communication by multimodal chaining 41

Children's overextension as communication by multimodal chai...

引用

41st Annual Meeting of the cognitive science Society: Creativity + Cognition + Computation, CogSci 2019

作者： Junior, Renato Ferreira Pinto Xu, Yang Department of Computer Science University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

ISBN: (纸本)0991196775

Young children often stretch terms to novel objects when they lack the proper adult words-a phenomenon known as overextension. Psychologists have proposed that overextension relies on the formation of a chain complex, such that new objects may be linked to existing referents of a word based on a diverse set of relations including taxonomic, analogical, and predicate-based knowledge. We build on these ideas by proposing a computational framework that creates chain complexes by multimodal fusion of resources from linguistics, deep learning networks, and psychological experiments. We test our models in a communicative scenario that simulates linguistic production and comprehension between a child and a caretaker. Our results show that the multimodal semantic space accounts for substantial variation in children's overextension in the literature, and our framework predicts overextension strategies. This work provides a formal approach to characterizing linguistic creativity of word sense extension in early childhood. © cognitive science Society: Creativity + Cognition + Computation, CogSci *** rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

How nouns surface as verbs: Inference and generation in word class conversion 42

How nouns surface as verbs: Inference and generation in word...

引用

42nd Annual Meeting of the cognitive science Society: Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020

作者： Yu, Lei El Sanyoura, Lana Xu, Yang Department of Computer Science University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

Word class conversion refers to the extended use of a word from one grammatical class to another without overt morphological marking. Noun-to-verb conversion, or denominalization, is one form of word class conversion studied extensively in the literature. Previous work has suggested that novel denominal verb usages are comprehensible if the listener can compute the intended meaning based on shared knowledge with the speaker. However, no existing work has explored the computational mechanism under this proposal. We propose a frame-semantic generative model, Noun2Verb, that supports the inference and generation of novel denominal verb usages via semi-supervised learning. We evaluate this framework in a dataset of denominal verbs drawn from adults and children against a state-of-the-art model from natural language processing. Our results show that Noun2Verb aligns better with human interpretation and bridges the gap between machines and humans in lexical innovation. © 2020 The Author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ComR:a combined OWL reasoner for ontology classification

引用

Frontiers of computer science 2019年第1期13卷 139-156页

作者： Changlong WANG Zhiyong FENG Xiaowang ZHANG Xin WANG Guozheng RAO Daoxun FU School of Computer Science and Technology Tianjin UniversityTianjin 300072China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin 300072China School of Computer Science and Engineering Northwest Normal UniversityLanzhou 730070China

Ontology classification,the problem of computing the subsumption hierarchies for classes (atomic concepts),is a core reasoning service provided by Web Ontology Language (OWL)*** general-purpose OWL 2 reasoners employ sophisticated optimizations for classification,they are still not efficient owing to the high complexity of tableau algorithms for expressive ontologies. Profile-specific OWL 2 EL reasoners are efficient;however, they become incomplete even if the ontology contains only a small number of axioms that are outside the OWL 2 EL *** this paper,we present a technique that combines an OWL 2 EL reasoner with an OWL 2 reasoner for ontology classification of expressive *** optimize the workload,we propose a task decomposition strategy for identifying the minimal non-EL subontology that contains only necessary axioms to ensure *** the ontology classification,the bulk of the workload is delegated to an efficient OWL 2 EL reasoner and only the minimal non- EL subontology is handled by a less efficient OWL 2 *** proposed approach is implemented in a prototype ComR and experimental results show that our approach offers a substantial speedup in ontology *** the wellknown ontology NCI,the classification time is reduced by 96.9%(resp.83.7%)compared against the standard reasoner Pellet (*** modular reasoner MORe).

关键词： OWL ontology classification reasoner

来源：评论

学校读者我要写书评

暂无评论

Monitoring blood pressure through a single hybrid hemodynamic signal with a flexible optoelectronic patch

Device

引用

Device 2025年

作者： Zhong, Yizhou Zhang, Yongcao Pu, Jing Wustoni, Shofarul Uribe, Johana Lopez-Larrea, Naroa Marks, Adam McCulloch, Iain Mecerreyes, David Baran, Derya Inal, Sahika Organic Bioelectronics Laboratory Biological and Environmental Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Materials Science and Engineering Program (MSE) Physical Sciences and Engineering Division (PSE) KAUST Thuwal 23955-6900 Saudi Arabia POLYMAT University of the Basque Country UPV/EHU Avenida Tolosa 72 Guipuzcoa Donostia-San Sebastian 20018 Spain Department of Chemistry University of Oxford Oxford OX1 3TF United Kingdom Andlinger Center for Energy and the Environment and Department of Electrical and Computer Engineering Princeton University Princeton 08544 NJ United States IKERBASQUE Basque Foundation for Science Plaza Euskadi 5 Bilbao 48009 Spain

Hemodynamics, the study of blood flow and circulatory forces, is fundamental for assessing cardiovascular health, disease states, and therapeutic outcomes. Here, we introduce a skin-conformable organic optoelectronic thin-film patch (ePatch) designed to simultaneously capture electrocardiography (ECG) and photoplethysmography (PPG) signals as a single hybrid signal, named the electrocardio-photoplethysmogram (EC-PPG). The ePatch integrates an organic electrochemical transistor (OECT), an organic photodiode, surface-mounted light-emitting diodes, and electrochemical electrodes on a flexible, skin-conforming substrate. By training deep learning models on the hybrid EC-PPG data, we achieved accurate arterial blood pressure estimations, with mean errors of just 1.69 mmHg for systolic and 0.89 mmHg for diastolic blood pressure, outperforming traditional predictions that rely on individual physiological signals as inputs. Our findings underscore the potential of EC-PPG as a compound hemodynamic signal for AI-driven vital sign monitoring and integrated, solution-processable soft electronics for clinical and point-of-care applications. © 2025 The Authors

关键词： DTI-3: Develop electrocardiography electrophysiology flexible electronics OECT OPD organic electrochemical transistor photoplethysmography wearable electronics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and Data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

2024 7th International Conference on Healthcare Service Management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

The GLAIR cognitive architecture

引用

International Journal of Machine Consciousness 2010年第2期2卷 307-332页

作者： Shapiro, Stuart C. Bona, Jonathan P. Department of Computer Science and Engineering Center for Cognitive Science State University of New York at Buffalo Buffalo NY 14260-2000 United States

GLAIR (Grounded Layered Architecture with Integrated Reasoning) is a multilayered cognitive architecture for embodied agents operating in real, virtual, or simulated environments containing other agents. The highest layer of the GLAIR Architecture, the Knowledge Layer (KL), contains the beliefs of the agent, and is the layer in which conscious reasoning, planning, and act selection is performed. The lowest layer of the GLAIR Architecture, the Sensori-Actuator Layer (SAL), contains the controllers of the sensors and effectors of the hardware or software robot. Between the KL and the SAL is the Perceptuo-Motor Layer (PML), which grounds the KL symbols in perceptual structures and subconscious actions, contains various registers for providing the agent's sense of situatedness in the environment, and handles translation and communication between the KL and the SAL. The motivation for the development of GLAIR has been "Computational Philosophy", the computational understanding and implementation of human-level intelligent behavior without necessarily being bound by the actual implementation of the human mind. Nevertheless, the approach has been inspired by human psychology and biology. © 2010 World Scientific Publishing Company.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Electroencephalogram and Event-Related Potential in Mild cognitive Impairment: Recent Developments in Signal Processing, Machine Learning, and Deep Learning

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2025年 2卷 162-184页

作者： Azami, Hamed Mirjalili, Mina Rajji, Tarek K. Wu, Chien-Te Humeau-Heurtier, Anne Jung, Tzyy-Ping Wei, Chun-Shu Trinh, Thanh-Tung Liu, Yi-Hung University of Toronto Centre for Addiction and Mental Health TorontoONM5S 1A1 Canada University of Texas Southwestern Medical Center DallasTX75390 United States University of Florida Department of Occupational Therapy GainesvilleFL32611 United States University of Florida Center for Cognitive Aging and Memory McKnight Brain Institute GainesvilleFL32611 United States University of Angers LARIS SFR MATHSTIC AngersF-49000 France University of California Institute for Neural Computation Institute of Engineering in Medicine La Jolla CA92093 United States National Yang Ming Chiao Tung University Department of Computer Science Hsinchu City30010 Taiwan National Taipei University of Technology Graduate Institute of Manufacturing Technology College of Mechanical and Electrical Engineering Taipei10608 Taiwan Vietnam National University Department of Information and Communication Technology Faculty of Nontraditional Security HSB Hanoi720325 Viet Nam National Yang Ming Chiao Tung University Institute of Electrical and Control Engineering Hsinchu City30010 Taiwan

Mild cognitive impairment (MCI) is an early stage of non-age-related cognitive decline with an increased risk of progressing to dementia. Early detection of MCI is essential for implementing preventative strategies that can delay or prevent the onset of dementia, ultimately improving patient outcomes and reducing healthcare costs. Electroencephalograms (EEGs) and event-related potentials (ERPs) have shown significant promise in detecting MCI due to their affordability, real-time monitoring capabilities, and noninvasiveness. EEG provides continuous brain activity data, while ERPs offer insights into specific cognitive processes by analyzing brain responses to stimuli. These methods can complement each other in MCI diagnosis by providing a comprehensive view of overall brain function and detailed information on specific cognitive processes. However, EEG and ERP are susceptible to noise and interindividual variability, which can hinder their reliability. In addition, applying machine learning models on EEG or ERP for MCI detection presents challenges such as the risk of overfitting and difficulties in interpreting the underlying decision-making process. This review emphasizes recent advancements in signal processing and feature extraction methods applied to EEG and ERP data and explores the use of machine learning and deep learning techniques to enhance diagnostic accuracy and interpretative depth. By integrating these methodologies, the review highlights how EEG and ERP can contribute to a more effective understanding and monitoring of cognitive changes associated with MCI, underscoring the importance of early diagnosis for timely intervention and improved patient care. Finally, the review focuses on future research directions, including the development of advanced analytical techniques and multimodal integration approaches involving EEG and ERP to further improve diagnostic accuracy and clinical application. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Evolvable dialogue state tracking for statistical dialogue management

引用

Frontiers of computer science 2016年第2期10卷 201-215页

作者： Kai YU Lu CHEN Kai SUN Qizhe XIE Su ZHU Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive EngineeringSpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China Department of Computer Science Cornell University Ithaca NY 14853 USA

Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking （DST） is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges （DSTC） have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. This makes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.

关键词： dialogue management domain extension,evolvable dialogue state tracking parser tracker

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：