ISO-learning approximates a solution to the inverse controller problem in an unsupervised behavioural paradigm.

Bernd Porr and Florentin Wörgötter

Neural Comp. 15, 865-884.

Download: PDF

In the previous article we have introduced an isotropic algorithm for temporal sequence learning (ISO-learning). Here we embed this algorithm into a formal non-evaluating ( teacher-free ) environment which establishes a sensor-motor feedback. The system is initially guided by a fixed reflex reaction which has the objective disadvantage that it can only react after a disturbance has occurred. ISOlearning eliminates this disadvantage by replacing the reflex-loop reactions with earlier anticipatory actions. In this article we will analytically demonstrate that this process can be understood in terms of control theory showing that the system learns the inverse controller of its own reflex. Thereby this system is able to learn a simple form feed-forward motor control.

More about ISO-learning: Films, circuit diagrams, etc, ...


Bernd Porr
Last modified: Wed Mar 17 17:53:49 GMT 2004