J. Rabit

Learn More
This paper presents experimental results of an original approach to the Neural Network learning architecture for the control and the adaptive control of mobile robots. The basic idea is to use non-recurrent multi-layer-network and the backpropagation algorithm without desired outputs, but with a quadratic criterion which spezify the control objective. To(More)
In two dispatching centers, 50 recordings were obtained from 14 workers. The recorded parameters were 2 EEG, 1 ECG, 1 EOG and 1 EMG; the whole day was covered by the various shifts. The results presented here are about the occipito-vertex EEG. After recording, a Fast Fourier Transform was done and the variations of the parameters beta1, beta2 and delta were(More)
  • 1