Rudolf Sollacher

Learn More
Distributed intelligent systems like self-organizing wireless sensor and actuator networks are supposed to work mostly autonomous even under changing environmental conditions. This requires robust and efficient self-learning capabilities implementable on embedded systems with limited memory and computational power. We present a new solution called Spiral(More)
As a representative of a complex technological system, so-called wireless multihop ad hoc communication networks are discussed. They represent an infrastructure-less generalization of todays wireless cellular phone networks. Lacking a central control authority, the ad hoc nodes have to coordinate themselves such that the overall network performs in an(More)
Autonomous, self* sensor networks require sensor nodes with a certain degree of " intelligence ". An elementary component of such an " intelligence " is the ability to learn online predicting sensor values. We consider recurrent neural network (RNN) models trained with an extended Kalman filter algorithm based on real time recurrent learning (RTRL) with(More)
Frequently, sequences of state transitions are triggered by specific signals. Learning these triggered sequences with recurrent neu-ral networks implies storing them as different attractors of the recurrent hidden layer dynamics. A challenging test and also useful for application is conditional prediction of sequences giving just the trigger signal as an(More)
In principle every excitation acquires a finite lifetime in a hot system. This nonzero spectral width is calculated self-consistently for massive fermions coupled to massless scalar, vector and pseudoscalar bosons. It is shown that the self-consistent summation of the corresponding Fock diagram for fermions eliminates all infrared divergences although the(More)