FPGA accelerated deep learning radio modulation classification using MATLAB system objects & PYNQ

Research output: Contribution to conferencePoster

13 Downloads (Pure)

Abstract

Deep learning (DL) and Artificial Intelligence (AI) have proven to be exciting and powerful machine learning-based techniques that have solved many real world challenges. They have made their mark in the image and video processing and natural language processing fields and now seek to make an impact on radio communications. With the increasing demand of high quality wireless data processing for spectrum sensing; cognitive radio; and accurate channel estimation, DL techniques could be used as the new state of the art answers to these problems.
Original languageEnglish
Number of pages1
Publication statusPublished - 10 Sep 2019
Event29th International Conference on Field-Programmable Logic and Applications - Barcelona Supercomputing Center and Universitat Politècnica de Catalunya, Barcelona, Spain
Duration: 9 Sep 201911 Sep 2019

Conference

Conference29th International Conference on Field-Programmable Logic and Applications
Abbreviated titleFPL 2019
CountrySpain
CityBarcelona
Period9/09/1911/09/19

Keywords

  • deep learning
  • machine learning
  • radio
  • communications

Fingerprint Dive into the research topics of 'FPGA accelerated deep learning radio modulation classification using MATLAB system objects & PYNQ'. Together they form a unique fingerprint.

  • Research Output

    Open Access
    File
  • Cite this

    Maclellan, A., McLaughlin, L., Crockett, L., & Stewart, R. W. (2019). FPGA accelerated deep learning radio modulation classification using MATLAB system objects & PYNQ. Poster session presented at 29th International Conference on Field-Programmable Logic and Applications, Barcelona, Spain.