Constrained Extreme Learning Machines: A Study on Classification Cases
This work addresses a bottleneck in pattern recognition for real-time applications by improving ELM efficiency, though it is incremental as it builds on existing ELM methods.
The paper tackled the issue of extreme learning machines (ELMs) requiring many hidden neurons for good generalization, which slows real-time testing, by proposing constrained extreme learning machines (CELMs) that randomly select hidden neurons based on sample distribution. The results show CELMs achieve better generalization than traditional ELM, SVM, and other methods while maintaining similar fast learning speed.
Extreme learning machine (ELM) is an extremely fast learning method and has a powerful performance for pattern recognition tasks proven by enormous researches and engineers. However, its good generalization ability is built on large numbers of hidden neurons, which is not beneficial to real time response in the test process. In this paper, we proposed new ways, named "constrained extreme learning machines" (CELMs), to randomly select hidden neurons based on sample distribution. Compared to completely random selection of hidden nodes in ELM, the CELMs randomly select hidden nodes from the constrained vector space containing some basic combinations of original sample vectors. The experimental results show that the CELMs have better generalization ability than traditional ELM, SVM and some other related methods. Additionally, the CELMs have a similar fast learning speed as ELM.