Associative Neural Network for learning inverse kinematics

An associative neural network is inspired by the function and structure of neural network correlations in brain in order to simulate the short- and long-term memory of neural networks. One application for the associative neural network is to learn inverse kinematics models for redundant robots (where the robot possesses more degrees of freedom than it is needed to achieve a given task), which allows to learn and store multiple solutions and favor between them depending on the initial state.
References:
http://www.rob.cs.tu-bs.de/node/306
http://www.rob.cs.tu-bs.de/node/287
http://ieeexplore.ieee.org/abstract/document/6652566