NELGSep 25, 2016

The RNN-ELM Classifier

arXiv:1609.07724v13 citations
Originality Incremental advance
AI Analysis

This work addresses the need for efficient and high-performance classification methods in machine learning, though it appears incremental as it builds on existing RNN and ELM techniques.

The paper tackles the problem of achieving state-of-the-art classification performance with reduced training time by combining the Random Neural Network (RNN) and Extreme Learning Machine (ELM), showing that this hybrid method outperforms ELM with other activation functions and compares favorably to autoencoder-based versions.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes