ABSTRACT
This work presents a large margin learning algorithm for single
hidden layer feedforward networks (SLFNs) with random weights
for the hidden neurons, called RP-IMA. This algorithm, applied to
binary classification problems, proposes randomly assignedweights
to the hidden layer and the use of an incremental margin algorithm
to calculate the weights of the output neuron of the SLFN. The
results showed that the proposed algorithm is capable to obtain
a large separation margin in the feature space and has its performance
less sensitive to variations in the network architecture, when
compared to Extreme Learning Machines.