LARSEN-ELM: Selective Ensemble of Extreme Learning Machines using LARS for Blended Data
This is an incremental improvement for machine learning practitioners dealing with blended data using ELM.
The paper tackled the weak robustness of Extreme Learning Machines (ELM) for blended data by proposing LARSEN-ELM, which uses LARS for variable selection and a Genetic Algorithm-based selective ensemble, resulting in significantly improved robustness while maintaining high speed compared to original ELM and other methods.
Extreme learning machine (ELM) as a neural network algorithm has shown its good performance, such as fast speed, simple structure etc, but also, weak robustness is an unavoidable defect in original ELM for blended data. We present a new machine learning framework called LARSEN-ELM for overcoming this problem. In our paper, we would like to show two key steps in LARSEN-ELM. In the first step, preprocessing, we select the input variables highly related to the output using least angle regression (LARS). In the second step, training, we employ Genetic Algorithm (GA) based selective ensemble and original ELM. In the experiments, we apply a sum of two sines and four datasets from UCI repository to verify the robustness of our approach. The experimental results show that compared with original ELM and other methods such as OP-ELM, GASEN-ELM and LSBoost, LARSEN-ELM significantly improve robustness performance while keeping a relatively high speed.