Abstract
Support vector regression (SVR) is a state-of-the-art method for regression which uses the εsensitive loss and produces sparse models. However, non-linear SVRs are difficult to tune because of the additional kernel parameter. In this paper, a new parameter-insensitive kernel inspired from extreme learning is used for non-linear SVR. Hence, the practitioner has only two meta-parameters to optimise. The proposed approach reduces significantly the computational complexity yet experiments show that it yields performances that are very close from the state-of-the-art. Unlike previous works which rely on Monte-Carlo approximation to estimate the kernel, this work also shows that the proposed kernel has an analytic form which is computationally easier to evaluate. © 2011 Elsevier B.V.
Original language | English |
---|---|
Pages (from-to) | 2526-2531 |
Number of pages | 6 |
Journal | Neurocomputing |
Volume | 74 |
Issue number | 16 |
DOIs | |
Publication status | Published - Sept 2011 |
Externally published | Yes |
Keywords
- ELM kernel
- Extreme learning machine
- Infinite number of neurons
- Support vector regression