Emily Cawley, Alex Berian, Tamal Bose

Research output: Contribution to journalConference articlepeer-review


In modern communication systems, message signals are processed with modulation, coding, pulse shaping, etc. for efficient data transmission. Recently, machine learning techniques have been used to replace such signal processing algorithms. Radio Transformer Networks (RTNs) is a technique that can be used to model an entire communication system with neural networks encompassing transmitter, channel, and receiver. These models can then be trained as a whole to generate encoding schemes that are optimized for different channel conditions. In this paper, we incorporate parameter estimation in the receiver trained with the model. Recurrent layers are used to improve parameter estimates whereby the network has the opportunity to “think longer.” Simulation results are presented to illustrate the concepts.

Original languageEnglish (US)
Pages (from-to)282-286
Number of pages5
JournalProceedings of the International Telemetering Conference
StatePublished - 2022
Event57th Annual International Telemetering Conference, ITC 2022 - Glendale, United States
Duration: Oct 24 2022Oct 27 2022

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation
  • Computer Networks and Communications
  • Signal Processing


Dive into the research topics of 'DEEP THINKING MODELS FOR RADIO TRANSFORMER NETWORKS'. Together they form a unique fingerprint.

Cite this