ELM Neural Network With Local Connection

The rapid development of the Internet has produced a large amount of data information.How to use these data to mine useful information has become a hot topic in the society.The traditional neural network is criticized for its slow training,long time-consuming and easy to fall into local optimum.Extreme Learning Machine(ELM)is a new type of neural network with fast learning and generalization.Good merits have attracted the attention of many scholars.This paper is concerned with the sparsification of the input-hidden weights of ELM(Extreme Learning Machine).For ordinary feedforward neural networks,the sparsification is usually done by introducing certain regularization technique into the learning process of the network.But this strategy can not be applied for ELM,since the input-hidden weights of ELM are supposed to be randomly chosen rather than to be learned.To this end,we propose a modified ELM,called ELM-LC(ELM with local connections),which is designed for the sparsification of the input-hidden weights as follows: The hidden nodes and the input nodes are divided respectively into several corresponding groups,and an input node group is fully connected with its corresponding hidden node group,but is not connected with any other hidden node group.As in the usual ELM,the hidden-input weights are randomly given,and the hidden-output weights are obtained through a least square learning.In the numerical simulations on some benchmark problems,the new ELM-CL behaves better than the traditional ELM.This article is roughly divided into four parts.The first part introduces the related contents of the neural network and the background of the paper.The second part introduces the ELM algorithm and its advantages.The third part introduces the ELM-LC algorithm.The fourth part is the numerical experiment.It is performed on both the classification and regression data sets.