Abstract. As potential candidates for human cognition, connectionist models of sentence processing must learn to behave systematically by generalizing from a small traning set. It ...
The so called MSO-problem, – a simple superposition of two or more sinusoidal waves –, has recently been discussed as a benchmark problem for reservoir computing and was shown ...
We describe a method for enriching the output of a parser with information available in a corpus. The method is based on graph rewriting using memorybased learning, applied to dep...
One of the most difficult problems in using dynamic reservoirs like echo state networks for signal processing is the choice of reservoir network parameters like connectivity or spe...
Abstract. Reservoir computing approaches have been successfully applied to a variety of tasks. An inherent problem of these approaches, is, however, their variation in performance ...