Extreme Learning Machine with Local Connections

TL;DR

This paper introduces ELM-LC, a modified Extreme Learning Machine with local connections that sparsifies input-hidden weights by grouping nodes, leading to improved performance over traditional ELM in benchmark tests.

Contribution

The paper proposes a novel ELM variant with local connections that sparsifies input-hidden weights without learning them, enhancing performance.

Findings

ELM-LC outperforms traditional ELM on benchmark problems.

The method effectively sparsifies input-hidden weights.

Local connections improve learning efficiency.

Abstract

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.