Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate. Thus, boosting is a method for learning an ensemble of classifiers. While boosting has been shown to be very effective for decision trees, its impact on neural networks has not been extensively studied. We prove one important difference between sums of decision trees compared to sums of convolutional neural networks (CNNs) which is that a sum of decision trees cannot be represented by a single decision tree with the same number of parameters while a sum of CNNs can be represented by a single CNN. Next, using standard object recognition datasets, we verify experimentally the well-known result that a boosted ensemble of decision trees usually generalizes much better on testing data than a single decision tree with the same number of parameters. In contrast, using the same datasets and boosting algorithms, our experiments show the opposite to be true when using neural networks (both CNNs and multilayer perceptrons (MLPs)). We find that a single neural network usually generalizes better than a boosted ensemble of smaller neural networks with the same total number of parameters.
翻译:推动是一种方法,通过将许多“ 弱点” 假设进行线性结合,找到高度准确的假设,其中每个假设都可能是中度准确的。 因此, 提升是一种学习分类器集合的方法。 虽然提升已证明对决策树非常有效, 但对于神经网络的影响并没有进行广泛的研究。 我们证明决策树与进化神经网络(CNNs)总和之间的一个重大差别, 也就是说, 决策树的总和不能由具有相同参数的单一决定树代表, 而CNN的总和则由单一的CNN来代表。 下一步, 我们使用标准对象识别数据集, 实验性地核查众所周知的结果, 即: 增强决策树的集合通常比同一参数的单一决策树在测试数据方面要好得多。 相比之下, 使用相同的数据集和增强算法, 我们的实验显示, 当使用神经网络( CNN和多层摄取器( MLP) 的总和时, 我们发现, 一个单一神经网络的总数量通常比一般参数要好得多。