Learn More
which was originally proposed for " generalized " single-hidden layer feedfor-ward neural networks (SLFNs), provides efficient unified learning solutions for the applications of feature learning, clustering , regression and classification. Different from the common understanding and tenet that hidden neurons of neural networks need to be iteratively(More)
Extreme learning machine (ELM) was initially proposed for single-hidden-layer feedforward neural networks (SLFNs). In the hidden layer (feature mapping), nodes are randomly generated independently of training data. Furthermore, a unified ELM was proposed, providing a single framework to simplify and unify different learning methods, such as SLFNs, least(More)
Big dimensional data is a growing trend that is emerging in many real world contexts, extending from web mining, gene expression analysis, protein-protein interaction to high-frequency financial data. Nowadays, there is a growing consensus that the increasing dimensionality poses impeding effects on the performances of classifiers, which is termed as the(More)
Generic object recognition is the classification of an individual object to a generic category. Intra-class variabilities, such as different objects of the same category, different poses and lighting conditions, cause big troubles for this task. Traditional methods involve plenty of pre-processing steps, such as shape model construction, extraction of(More)
  • 1