Model-based deep learning: Key approaches and design guidelines

Nir Shlezinger, Jay Whang, Yonina C. Eldar, Alexandros G. Dimakis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations


Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Such model-based methods tend to be sensitive to inaccuracies and may lead to poor performance when real systems display complex or dynamic behavior. On the other hand, purely data-driven approaches are becoming increasingly popular. Deep neural networks (DNNs) employ a highly flexible function class to learn mappings from data, and demonstrate excellent performance. However, DNNs typically require massive amounts of data and immense computational resources, limiting their applicability for some signal processing scenarios. We consider hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches. Such model-based deep learning methods exploit both partial domain knowledge, via mathematical structures designed for specific problems, as well as learning from limited data. Here, we survey leading approaches for studying and designing model-based deep learning systems, along with concrete design guidelines and signal processing oriented examples.

Original languageEnglish
Title of host publication2021 IEEE Data Science and Learning Workshop, DSLW 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665428255
StatePublished - 5 Jun 2021
Event2021 IEEE Data Science and Learning Workshop, DSLW 2021 - Toronto, Canada
Duration: 5 Jun 20216 Jun 2021

Publication series

Name2021 IEEE Data Science and Learning Workshop, DSLW 2021


Conference2021 IEEE Data Science and Learning Workshop, DSLW 2021


  • Model-based deep learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems
  • Education


Dive into the research topics of 'Model-based deep learning: Key approaches and design guidelines'. Together they form a unique fingerprint.

Cite this