Extreme Learning Machine (ELM) diagram can be created using free tools like EdrawMax. As suggested in the diagram, ELM is a feedforward neural network 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 need not be tuned. As the below image suggests, ELM is used as a single hidden layer feedforward network, including but not limited to sigmoid networks, RBF networks, threshold networks, fuzzy inference networks, complex neural networks, and wavelet networks. The hidden node in the extreme learning machine is a computational element that needs not be considered a classical neuron. A hidden node in ELM can be a classical artificial neuron or a subnetwork formed by some hidden nodes.
