RMDL: Random Multimodel Deep Learning for Classification

TL;DR

RMDL introduces an ensemble deep learning framework that automatically finds optimal architectures, enhancing robustness and accuracy across diverse data types like images and text.

Contribution

The paper presents RMDL, a novel ensemble deep learning approach that automatically optimizes architectures for improved classification performance.

Findings

RMDL outperforms standard methods on image datasets like MNIST and CIFAR-10.

RMDL achieves superior results on text datasets such as Reuters and IMDB.

The approach demonstrates versatility across multiple data types and classification tasks.

Abstract

The continually increasing number of complex datasets each year necessitates ever improving machine learning methods for robust and accurate categorization of these data. This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. Deep learning models have achieved state-of-the-art results across many domains. 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. RDML can accept as input a variety data to include text, video, images, and symbolic. This paper describes RMDL and shows test results for image and text data including MNIST, CIFAR-10, WOS, Reuters, IMDB, and 20newsgroup. These test results show that RDML produces consistently better performance than standard methods over a broad range of data types and classification problems.