RMDL: Random Multimodel Deep Learning for Classification

, , , ,  -

Publications: International Conference on Information System and Data Mining, arXiv Add/Edit

Abstract: Add/Edit

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.

Keywords: CNN: Convolutional Neural Networks, Data Mining, Text Classification, Image Classification, Deep Learning, Supervised Learning Add/Edit

Code Links
github.com: /kk7nc/RMDL

Languages: Python Add/Edit

Libraries: TensorFlow, Keras, sklearn Add/Edit

Description: Add/Edit

RMDL: Random Multimodel Deep Learning for Classification