Voting Based Neural Network: Extreme Learning Machine Essay

571 Words 3 Pages
Extreme learning Machine (ELM) [1] is a single hidden layer feed forward network (SLFN) introduced by G. B. Huang in 2006. In ELM, the weights between input and hidden neurons and the bias for each hidden neuron are assigned randomly. The weight between output neurons and hidden neurons are generated using the Moore Penrose Generalized Inverse [18]. This makes ELM a fast learning classifier. It surmounts various traditional gradient based learning algorithms [1] such as Back Propagation (BP) and well known classifier Support Vector Machine (SVM) .
In order to improve the performance various variants of the ELM came over time such as Enhanced Incremental ELM (EI-ELM)[2], Optimal Pruned ELM (OP-ELM) [3], Convex Incremental ELM (CI-ELM)[4], Error-Minimized ELM (EM-ELM) [5], Bidirectional ELM (B-ELM)[6], Online Sequential ELM (OS-ELM)[7]. Ensembling methods such as bagging [] and boosting [] have also been applied over ELM to improve its performance. Bagging based ELM is also known as Voting based ELM (V-ELM) [8]. Instances lying on the classification boundary are generally misclassified by ELM. These instances are classified correctly by V-ELM. Boosting methods has been applied over ELM to further improve the learning speed and for better generalization. Modified Adaboost based ELM [9], Dynamic Adaboost Ensemble based ELM[10] are some of the extensions of ELM.
Although V-ELM has improved the generalization ability of the ELM, but along with that the cost in term of number of…

More about Voting Based Neural Network: Extreme Learning Machine Essay