AdaBoost-assisted Extreme Learning Machine for Efficient Online Sequential Classification
This work addresses efficient online learning for sequential data, but it appears incremental as it combines existing techniques like AdaBoost and extreme learning machines.
The paper tackles the problem of online sequential classification by proposing an AdaBoost-assisted extreme learning machine with a forgetting mechanism, achieving 94.41% accuracy on MNIST and reducing accuracy standard deviation by 8.26x.
In this paper, we propose an AdaBoost-assisted extreme learning machine for efficient online sequential classification (AOS-ELM). In order to achieve better accuracy in online sequential learning scenarios, we utilize the cost-sensitive algorithm-AdaBoost, which diversifying the weak classifiers, and adding the forgetting mechanism, which stabilizing the performance during the training procedure. Hence, AOS-ELM adapts better to sequentially arrived data compared with other voting based methods. The experiment results show AOS-ELM can achieve 94.41% accuracy on MNIST dataset, which is the theoretical accuracy bound performed by an original batch learning algorithm, AdaBoost-ELM. Moreover, with the forgetting mechanism, the standard deviation of accuracy during the online sequential learning process is reduced to 8.26x.