Guner Orhan

Learn More
In this work, we model context in terms of a set of concepts grounded in a robot's sensorimotor interactions with the environment. For this end, we treat context as a latent variable in Latent Dirichlet Allocation, which is widely used in computational linguistics for modeling topics in texts. The flexibility of our approach allows many-to-many(More)
In cognitive robotics community, categories belonging to adjectives and nouns have been learned separately and independently. In this article, we propose a prototype-based framework that conceptualize adjectives and nouns as separate categories that are, however, linked to and interact with each other. We demonstrate how this co-learned concepts might be(More)
—It is now widely accepted that concepts and con-ceptualization are key elements towards achieving cognition on a humanoid robot. An important problem on this path is the grounded representation of individual concepts and the relationships between them. In this article, we propose a probabilistic method based on Markov Random Fields to model a concept web(More)
—In this article, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field, inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet(More)
  • 1