IEEE Trans Cybern. 2016 Jan;46(1):311-24. doi: 10.1109/TCYB.2015.2401973. Epub 2015 Mar 2.
In this paper, we propose a novel extension of the extreme learning machine (ELM) algorithm for single-hidden layer feedforward neural network training that is able to incorporate subspace learning (SL) criteria on the optimization process followed for the calculation of the network's output weights. The proposed graph embedded ELM (GEELM) algorithm is able to naturally exploit both intrinsic and penalty SL criteria that have been (or will be) designed under the graph embedding framework. In addition, we extend the proposed GEELM algorithm in order to be able to exploit SL criteria in arbitrary (even infinite) dimensional ELM spaces. We evaluate the proposed approach on eight standard classification problems and nine publicly available datasets designed for three problems related to human behavior analysis, i.e., the recognition of human face, facial expression, and activity. Experimental results denote the effectiveness of the proposed approach, since it outperforms other ELM-based classification schemes in all the cases.
在本文中，我们提出了一种极端学习机（ELM）算法的新扩展，用于单隐层前馈神经网络训练，该算法能够在网络输出权重的计算过程中结合子空间学习（SL）准则。所提出的图嵌入 ELM（GEELM）算法能够自然地利用在图嵌入框架下设计的内在和惩罚 SL 准则。此外，我们扩展了所提出的 GEELM 算法，以便能够在任意（甚至无限）维度的 ELM 空间中利用 SL 准则。我们在八个标准分类问题和九个公开可用的数据集上评估了所提出的方法，这些数据集是为与人类行为分析相关的三个问题设计的，即人脸识别、面部表情和活动识别。实验结果表明了所提出方法的有效性，因为它在所有情况下都优于其他基于 ELM 的分类方案。
