An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)

TL;DR

This paper presents Random Multimodel Deep Learning (RMDL), an ensemble approach that trains multiple deep learning models with different architectures to enhance classification accuracy and robustness across various datasets.

Contribution

The paper introduces RMDL, a novel ensemble deep learning method that automatically generates and combines diverse models for improved classification performance.

Findings

RMDL outperforms individual models in image and text classification.

Ensemble approach improves robustness and accuracy.

Effective across multiple datasets including MNIST, CIFAR-10, and face recognition datasets.

Abstract

The exponential growth in the number of complex datasets every year requires more enhancement in machine learning methods to provide robust and accurate data classification. Lately, deep learning approaches have achieved surpassing results in comparison to previous machine learning algorithms. However, finding the suitable structure for these models has been a challenge for researchers. This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. RMDL solves the problem of finding the best deep learning structure and architecture while simultaneously improving robustness and accuracy through ensembles of deep learning architectures. In short, RMDL trains multiple randomly generated models of Deep Neural Network (DNN), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in parallel and combines their results to produce better result of any of those models individually. In this paper, we describe RMDL model and compare the results for image and text classification as well as face recognition. We used MNIST and CIFAR-10 datasets as ground truth datasets for image classification and WOS, Reuters, IMDB, and 20newsgroup datasets for text classification. Lastly, we used ORL dataset to compare the model performance on face recognition task.