Extreme learning machines are feedforward neural networks for classification, regression, clustering, sparse approximation, compression and feature learning with a single layer or multiple layers of hidden nodes, where the parameters of hidden nodes (not just the weights connecting inputs to hidden nodes) need to be tuned. These hidden nodes can be randomly assigned and never updated (i.e. they are random projection but with nonlinear transforms), or can be inherited from their ancestors without being changed. In most cases, the output weights of hidden nodes are usually learned in a single step, which essentially amounts to learning a linear model.
The name "extreme learning machine" (ELM) was given to such models by Guang-Bin Huang. The idea goes back to Frank Rosenblatt, who not only published a single layer Perceptron in 1958, but also introduced a multi layer perceptron with 3 layers: an input layer, a hidden layer with randomized weights that did not learn, and a learning output layer.
According to some researchers, these models are able to produce good generalization performance and learn thousands of times faster than networks trained using backpropagation. In literature, it also shows that these models can outperform support vector machines in both classification and regression applications.
From 2001-2010, ELM research mainly focused on the unified learning framework for "generalized" single-hidden layer feedforward neural networks (SLFNs), including but not limited to sigmoid networks, RBF networks, threshold networks, trigonometric networks, fuzzy inference systems, Fourier series, Laplacian transform, wavelet networks, etc. One significant achievement made in those years is to successfully prove the universal approximation and classification capabilities of ELM in theory.
From 2010 to 2015, ELM research extended to the unified learning framework for kernel learning, SVM and a few typical feature learning methods such as Principal Component Analysis (PCA) and Non-negative Matrix Factorization (NMF).