Fast initialization for cascade-correlation learning
Fast initialization for cascade-correlation learning
复制标题
级联相关学习的快速初始化
DOI：
10.1109/72.750570
复制
发表时间：
1999
影响因子：
--
通讯作者：
M. Lehtokangas
中科院分区：
文献类型：
--
作者：
M. Lehtokangas
考虑了级联相关学习中的权值初始化。以往的研究大多采用候选训练来解决级联相关学习中的初始化问题。首先训练几个候选隐藏单元，然后将产生协方差标准的最佳值的隐藏单元安装到网络中。在有许多候选单元要训练的情况下，训练的总计算成本可能变得非常大。在这里，我们考虑了一种新的方法在级联相关学习的权重初始化。所提出的方法是基于逐步回归的概念。实验结果表明，与使用候选训练集的情况相比，新方法可以显著提高级联相关学习的速度。此外，总体表现保持类似或甚至优于候选人培训。
Weight initialization in the cascade-correlation learning is considered. Most of the previous studies use the so called candidate training to deal with the initialization problem in the cascade-correlation learning. There several candidate hidden units are first trained, and then the one yielding the best value for the covariance criterion is installed to the network. In case there are many candidate units to be trained, the total computational cost of the training can become very large. Here we consider a new approach for weight initialization in the cascade-correlation learning. The proposed method is based on the concept of stepwise regression. Empirical simulations show that the new method can significantly speed-up the cascade-correlation learning compared to the case where the candidate training is used. Moreover, the overall performance remained similar or was even better than with the candidate training.