Adaptation of Learning Rule Parameters Using a Meta Neural Network
作者:
Colin Mccormack,
期刊:
Connection Science
(Taylor Available online 1997)
卷期:
Volume 9,
issue 1
页码: 123-136
ISSN:0954-0091
年代: 1997
DOI:10.1080/095400997116775
出版商: Taylor & Francis Group
关键词: Supervisor Network;Resilient Backpropagation;Quickpropagation
数据来源: Taylor
摘要:
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.
点击下载:
PDF (185KB)
返 回