RMDL: Random Multimodel Deep Learning for Classification

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.

arXiv commentBest Paper award ACM ICISDM

References in corpus (2)

• Machine Learning in Automated Text Categorization
• PCANet: A Simple Deep Learning Baseline for Image Classification?

Cited by in corpus (8)

• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
• SpinalNet: Deep Neural Network with Gradual Input
• Analysis of Railway Accidents' Narratives Using Deep Learning
• Ensemble learning in CNN augmented with fully connected subnetworks
• An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
• Deep Learning Based Multi-Label Text Classification of UNGA Resolutions
• A Novel Framework for Neural Architecture Search in the Hill Climbing Domain
• Gender Detection on Social Networks using Ensemble Deep Learning