In the preceding chapter, we proposed a generic neuro-fuzzy device capable of communicating with its human (user) environment using natural language. While interacting with the user, the device follows the conversation's context and understands the meaning of each sentence, and learns persistently, resulting in an environment-dependent evolution and behavior. In this chapter, we introduce two novel fuzzy learning algorithms that the neuro-fuzzy device uses to learn new abstract terms and to adjust existing ones in the course of performing its task. We refer to the acquisition of new terms as innovative learning and to the on-line adjustment of previously acquired terms as progressive learning. We then present a real-world application, color selection, to demonstrate the principles of the device. Color selection is naturally visual, quite confined, and is very rich with a variety of abstract terms, both the colors and the operations applied to them.
CITATION STYLE
Ferri, E., & Langholz, G. (2000). Neuro-Fuzzy Approach to Natural Language Understanding and Processing (pp. 261–280). https://doi.org/10.1007/978-1-4615-4401-2_9
Mendeley helps you to discover research relevant for your work.