A Modified more Rapid Sequential Extreme Learning Machine

摘要

The speed of machine learning has been a concern of the people. The speed of Extreme Learning Machine (ELM) has been improved very faster than others. However, the speed of Sequential Extreme Learning Machine is still slow. So, a fast sequence Extreme Learning Machine (Fast Sequential Extreme Learning Machine, FS-ELM) is present by the use of iterative calculation in calculation of the output weights at obtaining input weights and hidden bias randomly. Independent parts of data on the hidden layer are superimposed after acquiring the sequence training data. Then the output weights are obtained with calculation formula. In the initialization of the learning phase during training FS-ELM can accept any number of training data without affecting the accuracy of training and test impact. FS-ELM has a faster speed increase compared to OS-ELM in data training, and it ensure the test accuracy is quite similar comparing with ELM and Online Sequence Extreme Learning Machine OS-ELM. In order to verify the speed and accuracy performance which FS-ELM possesses, a number of adequate comparative experiments on different scale datasets are conducted.