Abstract
This paper presents a new regularization for Extreme Learning Machines (ELMs). ELMs are Randomized Neural Networks (RNNs) that are known for their fast training speed and good accuracy. Nevertheless the complexity of ELMs has to be selected, and regularization has to be performed in order to avoid underfitting or overfitting. Therefore, a novel Regularization is proposed using a modified Lanczos Algorithm: Iterative Lanczos Extreme Learning Machine (Lan-ELM). As summarized in the experimental Section, the computational time is on average divided by 4 and the Normalized MSE is on average reduced by 11%. In addition, the proposed method can be intuitively parallelized, which makes it a very valuable tool to analyze huge data sets in real-time.
Original language | English |
---|---|
Peer-reviewed scientific journal | Neurocomputing |
Volume | 414 |
Pages (from-to) | 172-181 |
Number of pages | 10 |
ISSN | 0925-2312 |
DOIs | |
Publication status | Published - 14.07.2020 |
MoE publication type | A1 Journal article - refereed |
Keywords
- 113 Computer and information sciences
- Classification
- Extreme learning machines
- Lanczos algorithm
- Neural networks
- Regression
- Regularization