Extreme learning machine (ELM) is a recently developed training algorithm for single hidden layer feedforward neural networks (SLFNs). ELM theory claims that the hidden node parameters of SLFNs can be randomly generated and need not to be updated. All the hidden node parameters are independent of the target functions or the training datasets. Benefitting from the tuning-free framework, ELM not only learns up to thousands times faster than conventional gradient descent methods for SLFNs and the support vector machine (SVM) but also preserves a reasonable generalization performance. For most applications, it has been shown that the learning phase of ELM can be finished in less than one second in an ordinary PC. Therefore, ELM shows superiority over conventional gradient based methods and SVM on high dimensional applications and large data processing. This is especially important since nowadays data are explosive with the rapid development of the internet, computer, and electronic equipment.

With this objective, we initiate a special issue on ELM and its applications in high dimensional and large data problems. The aim of this special issue is to bring together the latest and innovative developments in theories and algorithms based on ELM for large data applications, such as image processing, video processing, bioinformatics applications, and human-computer interaction. All the submissions are expected to have original ideas and/or new approaches. All the submissions must be related to the ELM technique.

Potential topics include, but are not limited to:

• Real-time learning for large data applications
• ELM theory
• Convergence analysis of ELM algorithms
• Time-series prediction for large data applications
• ELM on image and video processing
• Bioinformatics and biometrics applications with ELM
• Human-computer interaction with ELM
• Web applications