: A new method for the characterization of molecules based on the model approach of molecular surfaces is presented. We use the topographical properties of the surface as well as t...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
In robot navigation tasks, the representation of the surrounding world plays an important role, especially in reinforcement learning approaches. This work presents a qualitative r...
ion mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving directio...
The important role given to domain ontologies for knowledge representation implies increasing need for development and maintenance of them. However, we have a scarcity of tools sup...