We present a connectionist approach to learn for-
ward and redundant inverse kinematics in a single recurrent
network. The network architecture extends the reservoir com-
puting idea, i.e. to read out the state of a fixed dynamic
system, into an associative setting, which learns the forward
and backward mapping simultaneously. For output learning we
use efficient Backpropagation-Decorrelation learning while the
recurrent dynamics is adjusted by an unsupervised biologically
inspired learning rule based on intrinsic plasticity. Including
linear connections between input and output allows to train the
network for autonomous movement generation. We show results
for the 7-DOF redundant PA-10 robot arm in simulation.
| 
