Evaluation of robustness and performance of Early Stopping Rules with Multi Layer Perceptrons
Evaluation of robustness and performance of Early Stopping Rules with Multi Layer Perceptrons
复制标题
使用多层感知器评估提前停止规则的鲁棒性和性能
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
T. Breuel
中科院分区：
文献类型：
--
作者：
A. Lodwich;Yves Rangoni;T. Breuel
在本文中，我们使用随机梯度下降（也称为在线错误反向传播）评估了不同的早期停止规则（ESR）及其组合，以停止多层感知训练（MLP），然后才达到预定义的最大数量。我们将评估集中在分类任务上，因为大多数作品都使用MLP进行分类而不是回归。早期停止很重要，原因有两个。一方面，它可以防止过度拟合，另一方面可以大大减少训练时间。如今，存在越来越多的申请，涉及无监督和自动培训（例如在整体学习中），在整体学习中，自动停止规则对于保持训练时间较低是必要的。当前的文献并不是关于认可使用哪种规则，何时使用它或其鲁棒性的特定特定的。因此，本文重新审视了这个问题。我们在UCI数据库和MNIST的集合中测试了Proben1。
In this paper, we evaluate different Early Stopping Rules (ESR) and their combinations for stopping the training of Multi Layer Perceptrons (MLP) using the stochastic gradient descent, also known as online error backpropagation, before reaching a predefined maximum number of epochs. We focused our evaluation to classification tasks, as most of the works use MLP for classification instead of regression. Early stopping is important for two reasons. On one hand it prevents overfitting and on the other hand it can dramatically reduce the training time. Today, there exists an increasing amount of applications involving unsupervised and automatic training like i.e. in ensemble learning, where automatic stopping rules are necessary for keeping training time low. Current literature is not so specific about endorsing which rule to use, when to use it or what its robustness is. Therefore this issue is revisited in this paper. We tested on PROBEN1, a collection of UCI databases and the MNIST.