Reinhart, René Felix2018-01-082018-01-0820122012https://dl.gi.de/handle/20.500.12116/11323This thesis presents a dynamical system approach to learning forward and inverse models in associative recurrent neural networks. Ambiguous inverse models are represented by multi-stable dynamics. Random projection networks, i.e. reservoirs, together with a rigorous regularization methodology enable robust and efficient training of multi-stable dynamics with application to movement control in robotics.Dynamical systemsMachine learningText/Journal Article1610-1987