Deep Learning on Cryptocurrency - Challenges Processing GPU and CPU Architectures

Document Type

Conference Proceeding

Publication Date

12-6-2021

Publication Title

IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Proceedings

DOI

10.1109/IEMCON53756.2021.9623132

Abstract

Deep learning has made vast advances over the recent decade due to hardware, software, and architecture improvements. Applying deep learning still has some challenges to overcome, especially when processing on GPU or in parallel. This work seeks to apply RNN and LSTM over a variety of architectures to demonstrate the challenges and techniques encountered when applying deep learning. We apply RNN and LSTM over GPU and CPU across PC, high performance computing cluster, and cloud and present our challenges and results.

Comments

Georgia Southern University faculty members, Hayden Wimmer and Weitian Tong co-authored Deep Learning on Cryptocurrency – Challenges Processing GPU and CPU Architectures.

Share

COinS