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

2018/08/01 by Mojtaba Heidarysafa, Kamran Kowsari, Donald E. Brown +2
Computer Science · Mathematics · #Artificial intelligence #Artificial neural network #Computer science #Contextual image classification #Convolutional neural network #Deep learning #Domain Adaptation and Few-Shot Learning #Ensemble learning #Face and Expression Recognition #Image (mathematics) #MNIST database #Machine learning #Pattern recognition (psychology) #Robustness (evolution) #Text and Document Classification Technologies #cs.CV #cs.IR #cs.LG #cs.NE #stat.ML

paper · pdf · doi:10.18178/ijmlc.2018.8.4.703

published in International Journal of Machine Learning and Computing (IJMLC). arXiv admin note: substantial text overlap with arXiv:1805.01890

openalex publication_date 2018/08/01 · arxiv created 2018/08/23 · arxiv updated 2018/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

• RMDL: Random Multimodel Deep Learning for Classification
• ADADELTA: An Adaptive Learning Rate Method
• Adam: A Method for Stochastic Optimization
• Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
• Deep Learning using Linear Support Vector Machines
• Efficient Estimation of Word Representations in Vector Space
• PCANet: A Simple Deep Learning Baseline for Image Classification?
• On the difficulty of training Recurrent Neural Networks
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Term-weighting approaches in automatic text retrieval
• A Statistical Approach to Mechanized Encoding and Searching of Literary Information
• Long Short-Term Memory
• Gradient-based learning applied to document recognition
• A STATISTICAL INTERPRETATION OF TERM SPECIFICITY AND ITS APPLICATION IN RETRIEVAL
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
• ImageNet classification with deep convolutional neural networks
• Glove: Global Vectors for Word Representation
• Deep learning