Date of Award

2-1-2023

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Computer Science

First Advisor

John Talburt

Abstract

Due to modern data collection practices, datasets can be both high dimensional and very large in size. With the production of these large, high dimensional datasets comes the task of analyzing them. Deep neural networks are often applied to high dimensional datasets in a supervised manner where a network is trained using labeled datasets and then applied to other, similar datasets. However, labeled datasets are often expensive to produce and are not always available for training purposes in all scenarios. For unlabeled datasets, unsupervised learning using data clustering is often the learning method of choice. Deep clustering is a relatively new technique developed to address this problem that combines the power of deep neural networks with clustering to provide an unsupervised method of learning from high dimensional datasets. However, previously proposed deep clustering methods lack the ability to cluster extremely large datasets. This dissertation proposes a novel parallel deep k-means algorithm that combines parallel training of a deep autoencoder with parallel clustering and applies the resulting algorithm to the problem of text classification and pattern recognition. The algorithm utilizes Apache Spark for parallel processing and TensorFlow for parallel training of a deep autoencoder and is shown to be both scalable and effective.

Download

Share

COinS