Context dependent learning in neural networks

In this paper an extension to the standard error back-propagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.