CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
Machine Learning
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Hi-index | 0.00 |
We describe a Bayesian network implementation of a theory of concepts that is motivated by observations from the philosophical debate between Lexical Concept Empiricism and Lexical Concept Nativism. According to our theory, Baptizing Meanings for Concepts (BMC), concepts are acquired by hypothesizing latent kinds/categories to explain observed cooccurrences of sets of properties in a group of objects. The hypothesized kind/category is given a name and inferential relationships are stored between the name and representations for the observable properties. We argue that this process appeases tensions in the philosophical debate by allowing for the acquisition of concepts via perception and inference, while yielding the concepts simple, in the sense of being contingently associated with other representations. The BMC is inspired by a well-known process in the philosophy of language for assigning meanings to linguistic terms [1, 2, 3, 4].