Voting Based Extreme Learning Machine Essay examples

562 Words 3 Pages
Real valued classification is a popular decision making problem, having wide practical application in various fields. Extreme Learning Machine (ELM) pro-
posed by Huang et al.[1], is an effective machine learning technique for real valued classification. ELMis a single hidden layer feedfo5 rward network in which the
weights between input and hidden layer are initialized randomly. ELM uses analytical approach to compute weights between hidden and output layer [2], which
makes it faster compared to other gradient based classifiers ([3, 4]). Various variants of ELM were recently proposed, which includes Incremental Extreme
10 Learning Machine [5], Kernelized Extreme Learning Machine [6], Weighted Extreme Learning Machine(WELM) [7], Regularized extreme learning machine
[8], Complex Extreme Learning Machine [2],Circular Complex valued Extreme Learning Machine(CC-ELM)[9] etc. This work is motivation of CC-ELM [9]
and WELM [7].
15 CC-ELM [9] is a complex variant of ELM which exploits capabilities of complex valued neuron and uses fully complex activation function. Complex
valued neural network have better computational power, faster convergence and better generalization ability [10, 11, 12] than real valued neural network.
Moreover, they have inherent orthogonal decision boundaries. For example, 20 EX-OR problem can be solved easily by using a single complex valued neuron
[13]. As a result of increase in the applications involving complex valued signals like…