Author： Mccormack Colin
Publisher： Taylor & Francis Ltd
ISSN： 1360-0494
Source： Connection Science, Vol.9, Iss.1, 1997-03, pp. : 123-136
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
This paper proposes an application-independent method of automating learning rule parameter selection using a form of supervisor neural network (NN), known as a meta neural network (MNN), to alter the value of a learning rule parameter during training. The MNN is trained using data generated by observing the training of a NN and recording the effects of the selection of various parameter values. The MNN is then combined with a normal learning rule to augment its performance. Experiments are undertaken to see how this method performs by using it to adapt a global parameter of the resilient backpropagation and quickpropagation learning rules.
Related content
Access to resources
Recommend
ADAPTATION BASED ON MEMORY DYNAMICS IN A CHAOTIC NEURAL NETWORK
By Crook Nigel Scheper Tjeerd Olde
Cybernetics and Systems, Vol. 33, Iss. 4, 2002-06 ,pp. :