基于资源分配网络的小数据集并行集成学习方法

机器学习领域中，如何在小规模的训练数据集上获得一个具有稳定的高计算精度的算法模型，一直以来都是一个棘手而富有挑战的问题。从算法模型出发，提出了一种基于扩展卡尔曼滤波器的资源分配网络并行集成学习方法。该集成系统由多个带有扩展卡尔曼滤波器的资源分配网络（RANEKF）组成，并且每个RANEKF子网的输入由原始数据集中的输入经过随机权值的修正得到。通过和其他神经网络构成的集成学习算法的实验对比，发现提出的方法在小训练集上拥有更高的计算精度和稳定性。

Parallel ensemble learning method based on resource allocating networks for small dataset

To design a training model with stable computational performance and high accuracy which is applied on a small training dataset has been a difficult and challenging problem in the field of machine learning. This paper proposed a Resource Allocating Networks with Extended Kalman Filter (RANEKFs) based parallel ensemble learning algorithm. The learning system is composed of multiple RANEKF units, and the unit inputs are produced by the original dataset with random initialized weights. Based on the experiment results conducted on a small dataset, it is found that the novel model outperforms the ensemble learning systems constructed by the other artificial neural networks in terms of the computational accuracy and stability.