The RNN-ELM Classifier

TL;DR

This paper introduces a novel classifier combining the Random Neural Network with Extreme Learning Machine, achieving high classification accuracy with reduced training time by leveraging biologically inspired models and dimensionality reduction techniques.

Contribution

The paper presents a new RNN-ELM classifier that integrates RNN-derived activation functions into ELM, improving efficiency and performance over traditional ELM methods.

Findings

RNN-ELM achieves state-of-the-art classification performance.

The method requires significantly less training time.

Dimensionality reduction enhances classifier performance.

Abstract

In this paper we examine learning methods combining the Random Neural Network, a biologically inspired neural network and the Extreme Learning Machine that achieve state of the art classification performance while requiring much shorter training time. The Random Neural Network is a integrate and fire computational model of a neural network whose mathematical structure permits the efficient analysis of large ensembles of neurons. An activation function is derived from the RNN and used in an Extreme Learning Machine. We compare the performance of this combination against the ELM with various activation functions, we reduce the input dimensionality via PCA and compare its performance vs. autoencoder based versions of the RNN-ELM.