With fast learning speed and high accuracy, extreme learning machine (ELM) has achieved great success in pattern recognition and machine learning. Unfortunately, it will fail in the circumstance where plenty of labeled samples for training model are insufficient. The labeled samples are difficult to obtain due to their high cost. In this paper, we solve this problem with transfer learning and propose joint transfer extreme learning machine (JTELM). First, it applies cross-domain mean approximation (CDMA) to minimize the discrepancy between domains, thus obtaining one ELM model. Second, subspace alignment (sa) and weight approximation are together introduced into the output layer to enhance the capability of knowledge transfer and learn another ELM model. Third, the prediction of test samples is dominated by the two learned ELM models. Finally, a series of experiments are carried out to investigate the performance of JTELM, and the results show that it achieves efficiently the task of transfer learning and performs better than the traditional ELM and other transfer or nontransfer learning methods.

中文翻译：

---

具有跨域均值逼近和输出权重对齐的联合迁移极限学习机

极限学习机（ELM）以其学习速度快、准确率高的特点在模式识别和机器学习领域取得了巨大的成功。不幸的是，在用于训练模型的大量标记样本不足的情况下，它会失败。由于成本高，标记的样本很难获得。在本文中，我们通过迁移学习解决了这个问题，并提出了联合迁移极限学习机（JTELM）。首先，它应用跨域均值近似（CDMA）来最小化域之间的差异，从而获得一个 ELM 模型。其次，将子空间对齐（sa）和权重近似一起引入输出层，以增强知识迁移能力并学习另一个 ELM 模型。第三，测试样本的预测由两个学习的 ELM 模型主导。最后，