Text
E-book Concepts in Action : Representation, Learning, and Application
It is impossible to talk about human cognition without talking about concepts—there simplyisno human cognition without concepts. Concepts form an abstractionof reality that is central to the functioning of the human mind. Conceptual knowledge(of e.g., APPLE, LOVE and BEFORE) is crucial for us to categorize, understand,and reason about the world. Only equipped with concepts and words for them can wesuccessfully communicate and carry out actions.But what exactly are concepts? Howare concepts acquired? How does the human mind use concepts?Such questions havebeen a subject of discussion since antiquity and remain highly relevant in multiplefields (e.g., Murphy2002; Margolis and Laurence2015).Recent decades have seen fruitful results and methodological advances on conceptresearch in disciplines such as linguistics, philosophy, psychology, artificial intelli-gence, and computer science. For instance, cognitive psychologists use empiricalexperiments to validate formal models of concept representation and learning suchas the prototype theory (Rosch et al.1976), the exemplar theory (Murphy2016)orotheralternativetheories(RogersandMcClelland2004;Blouwetal.2016).Linguistspursue the goal of assigning more precise meaning to natural language expressionsby mainly applying logic-based formalisms (Asher2011). In machine learning, deci-sion boundaries in high-dimensional feature spaces are used to define membershipto a concept (Mitchell1997). Moreover, researchers in the semantic web area have created large ontologies (Gómez-Pérez et al.2004) containing hierarchies of con-cepts formulated in description logics. Google’s “Knowledge Graph” illustrates howsuch ontologies can be used in industrial applications.
Tidak tersedia versi lain