Reprint

Knowledge Modelling and Learning through Cognitive Networks

Edited by
June 2022
240 pages
  • ISBN978-3-0365-4345-1 (Hardback)
  • ISBN978-3-0365-4346-8 (PDF)

This is a Reprint of the Special Issue Knowledge Modelling and Learning through Cognitive Networks that was published in

Computer Science & Mathematics
Summary

One of the most promising developments in modelling knowledge is cognitive network science, which aims to investigate cognitive phenomena driven by the networked, associative organization of knowledge. For example, investigating the structure of semantic memory via semantic networks has illuminated how memory recall patterns influence phenomena such as creativity, memory search, learning, and more generally, knowledge acquisition, exploration, and exploitation. In parallel, neural network models for artificial intelligence (AI) are also becoming more widespread as inferential models for understanding which features drive language-related phenomena such as meaning reconstruction, stance detection, and emotional profiling. Whereas cognitive networks map explicitly which entities engage in associative relationships, neural networks perform an implicit mapping of correlations in cognitive data as weights, obtained after training over labelled data and whose interpretation is not immediately evident to the experimenter. This book aims to bring together quantitative, innovative research that focuses on modelling knowledge through cognitive and neural networks to gain insight into mechanisms driving cognitive processes related to knowledge structuring, exploration, and learning. The book comprises a variety of publication types, including reviews and theoretical papers, empirical research, computational modelling, and big data analysis. All papers here share a commonality: they demonstrate how the application of network science and AI can extend and broaden cognitive science in ways that traditional approaches cannot.

Format
  • Hardback
License and Copyright
© 2022 by the authors; CC BY-NC-ND license
Keywords
text mining; big data; analytics; review; self-organization; computational philosophy; brain; synaptic learning; adaptation; functional plasticity; activity-dependent resonance states; circular causality; somatosensory representation; prehensile synergies; robotics; COVID-19; social media; hashtag networks; emotional profiling; cognitive science; network science; sentiment analysis; computational social science; sentiment analysis; Twitter; COVID-19; VADER scoring; correlation; semantic network analysis; intellectual disability; adolescents; EEG; emotional states; working memory; depression; anxiety; graph theory; classification; machine learning; neural networks; phonotactic probability; neighborhood density; sub-lexical representations; lexical representations; phonemes; biphones; network science; cognitive network; smart assistants; knowledge generation; intelligent systems; web components; deep learning; web-based interaction; cognitive network science; text analysis; natural language processing; artificial intelligence; emotional recall; cognitive data; AI; pharmacological text corpus; automatic relation extraction; natural language processing; deep learning; gender stereotypes; story tropes; movie plots; network analysis; word co-occurrence network; n/a

Related Books

December 2019

Knowledge Management, Innovation and Big Data

Social Sciences, Arts & Humanities
...
April 2024

Artificial Intelligence in Complex Networks

Social Sciences, Arts & Humanities
...
November 2023

New Insights in Machine Learning and Deep Neural Networks

Computer Science & Mathematics
April 2021

Innovative Topologies and Algorithms for Neural Networks

Public Health & Healthcare
...