Extreme learning machine based transfer learning for data classification

The extreme learning machine (ELM) is a new method for using Single-hidden Layer Feed-forward Networks (SLFNs) with a much simpler training method. While conventional extreme learning machine are based on the training and test data which should be under the same distribution, in reality it is often desirable to learn an accurate model using only a tiny amount of new data and a large amount of old data. Transfer learning (TL) aims to solve related but different target domain problems by using plenty of labeled source domain data. When the task from one new domain comes, new domain samples are relabeled costly, and it would be a waste to discard all the old domain data. Therefore, an algorithm called TL-ELM based on the ELM algorithm is proposed, which uses a small amount of target domain tag data and a large number of source domain old data to build a high-quality classification model. The method inherits the advantages of ELM and makes up for the defects that traditional ELM cannot transfer knowledge. Experimental results indicate that the performance of the proposed methods is superior to or at least comparable with existing benchmarking methods. In addition, a novel domain adaptation kernel extreme learning machine (TL-DAKELM) based on the kernel extreme learning machine was proposed with respect to the TL-ELM. Experimental results show the effectiveness of the proposed algorithm.