The novel use of an Extreme learning machines for clinical decision support systems

In this monthly issue of CMPB, we brought a wide range of interesting articles related with computer methods application in the clinical settings. However, this month’s editorial focus is on Extreme learning machines which are feedforward neural network for classification or regression with a single layer of hidden nodes, where the weights connecting inputs to hidden nodes are randomly assigned. A feedforward neural network is an artificial neural network wherein connections between the units do not form a cycle. As such, it is different from recurrent neural networks. The weights between hidden nodes and outputs are learned in a single step, which essentially amounts to learning a linear model. The creators of these models claims that these models are able to produce good generalization performance and learn thousands of times faster than networks trained using backpropagation.