2014 | OriginalPaper | Buchkapitel
A Neural Dynamic Architecture Resolves Phrases about Spatial Relations in Visual Scenes
verfasst von : Mathis Richter, Jonas Lins, Sebastian Schneegans, Gregor Schöner
Erschienen in: Artificial Neural Networks and Machine Learning – ICANN 2014
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
How spatial language, important to both cognitive science and robotics, is mapped to real-world scenes by neural processes is not understood. We present an autonomous neural dynamics that achieves this mapping flexibly. Neural activation fields represent and spatially transform perceptual information. An architecture of dynamic nodes interacts with these perceptual fields to instantiate categorical concepts. Discrete time processing steps emerge from instabilities of the time-continuous neural dynamics and are organized sequentially by these nodes. These steps include the attentional selection of individual objects in a scene, mapping locations to an object-centered reference frame, and evaluating matches to relational spatial terms. The architecture can respond to queries specified by setting the state of discrete nodes. It autonomously generates a response based on visual input about a scene.