Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
"KnowledgeMiner" was designed to support the knowledge extraction process on a highly automated level. Implemented are 3 different GMDH-type self-organizing modeling algo...
This paper introduces a novel parallelised vision based intelligent controller for a Humanoid Robot system. This intelligent controller is simulated dynamically and its performance...
We present an artificial neural network used to learn online complex temporal sequences of gestures to a robot. The system is based on a simple temporal sequences learning architec...
Prediction is an important task in robot motor control where it is used to gain feedback for a controller. With such a self-generated feedback, which is available before sensor rea...