Overview

Extreme Learning Machines(ELMs) [1] are a kind of neural network that differently from traditional networks, which train their hidden neurons, only train the final output weights. This means that instead of using techniques such as gradient descent, you can use a least-squares method to minimize error.

Installation

] add ExtremeLearning

References

[1] G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, "Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks", Proc. Int. Joint Conf. Neural Networks (IJCNN2004), vol. 2, IEEE, 2004, pp. 985-990.