Word embeddings can reflect the semantic representations, and the embedding qualities can be comprehensively evaluated with human natural reading-related cognitive data sources. In this paper, we proposed the CogniFNN framework, which is the first attempt at using fuzzy neural networks to extract non-linear and non-stationary characteristics for evaluations of English word embeddings against the corresponding cognitive datasets. In our experiment, we used 15 human cognitive datasets across three modalities: EEG, fMRI, and eye-tracking, and selected the mean square error and multiple hypotheses testing as metrics to evaluate our proposed CogniFNN framework. Compared to the recent pioneer framework, our proposed CogniFNN showed smaller prediction errors of both context-independent (GloVe) and context-sensitive (BERT) word embeddings, and achieved higher significant ratios with randomly generated word embeddings. Our findings suggested that the CogniFNN framework could provide a more accurate and comprehensive evaluation of cognitive word embeddings. It will potentially be beneficial to the further word embeddings evaluation on extrinsic natural language processing tasks.
Introducing Randomized High Order Fuzzy Cognitive Maps as Reservoir Computing Models: A Case Study in Solar Energy and Load Forecasting
Federal University of Minas Gerais(米纳斯吉拉斯联邦大学);Federal Institute of Education Science and Technology of Northern Minas Gerais(北米纳斯吉拉斯联邦教育科技学院);Universidade Federal de Minas Gerais(米纳斯吉拉斯联邦大学)
Combined-distance-based score function of cognitive fuzzy sets and its application in lung cancer pain evaluation
College of Management Science, Chengdu University of Technology(成都理工大学管理科学学院);School of Architecture and Civil Engineering, Chengdu University(成都大学建筑与土木工程学院)
Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent
Department of Electrical and Computer Engineering(电气与计算机工程系);University of Southern California(南加州大学);School of Computing and Information Sciences(计算与信息科学学院);Florida International University(佛罗里达国际大学)
Unconventional Cognitive Intelligent Robotic Control: Quantum Soft Computing Approach in Human Being Emotion Estimation -- QCOptKB Toolkit Application
Institute of System Analysis and Management, Dubna State University(杜布纳国立大学系统分析与管理研究所);Joint Institute for Nuclear Research (JINR)(联合核研究所);Moscow State University of Geodesy and Cartography (MIIGAiK)(莫斯科测绘与制图大学);Yamaha Motor Co. Ltd.(雅马哈发动机株式会社)
Accelerating Hybrid Agent-Based Models and Fuzzy Cognitive Maps: How to Combine Agents who Think Alike?
Virginia Modeling Analysis and Simulation Center(弗吉尼亚建模分析与仿真中心);Old Dominion University(奥多明尼昂大学);School of Data Science(数据科学学院);University of Virginia(弗吉尼亚大学)
On the Convergence of Sigmoid and tanh Fuzzy General Grey Cognitive Maps
School of Electronics and Information, Northwestern Polytechnical University(西北工业大学电子信息学院);Department of Data Science and AI, Monash University(莫纳什大学数据科学与人工智能系);School of Aeronautics, Northwestern Polytechnical University(西北工业大学航空学院);College of Intelligence Science and Technology, National University of Defense Technology(国防科技大学智能科学学院);Chongqing Institute for Brain and Intelligence(重庆脑与智能研究院)
本文研究 FGGCM 在 sigmoid 与 tanh 激活下的收敛条件,通过空间完备性与不动点定理给出唯一不动点判据,并以 Web Experience 和土木工程案例验证其推广性。
Context and Interference Effects in the Combinations of Natural Concepts
Center Leo Apostel for Interdisciplinary Studies, Brussels Free University(布鲁塞尔自由大学利奥·阿波斯泰尔跨学科研究中心);KASK and Conservatory(KASK艺术学院与音乐学院);Laboratorio di Autoricerca di Base(基础自主研究实验室);School of Management and IQSCS, University of Leicester(莱斯特大学管理学院与IQSCS)
ActPC-Geom: Towards Scalable Online Neural-Symbolic Learning via Accelerating Active Predictive Coding with Information Geometry & Diverse Cognitive Mechanisms
A New Fundamental Evidence of Non-Classical Structure in the Combination of Natural Concepts
Center Leo Apostel for Interdisciplinary Studies, Brussels Free University(布鲁塞尔自由大学跨学科研究利奥·阿波斯泰尔中心);University of British Columbia, Okanagan Campus(不列颠哥伦比亚大学奥卡纳根校区);Instituto de Filosofía y Ciencias de la Complejidad (IFICC)(复杂性与哲学科学研究所)