Abstract. We present a system for automatically evolving neural networks as physics-based locomotion controllers for humanoid characters. Our approach provides two key features: (a...
We introduce a novel method for relational learning with neural networks. The contributions of this paper are threefold. First, we introduce the concept of relational neural networ...
Currently, fuzzy controllers are the most popular choice for hardware implementation of complex control surfaces because they are easy to design. Neural controllers are more compl...
Modeling studies have shown that recurrent interactions within neural networks are capable of self-sustaining non-uniform activity profiles. These patterns are thought to be the n...