JSAIT CFP: Deep Learning: Mathematical Foundations and Applications to Information Science

Jump to other IT Society Websites:
IEEE JSAIT's inaugural issue will be on Deep Learning: Mathematical Foundations and Applications to Information Science.

This special issue will focus on the mathematical foundations of deep learning as well as applications across information science. Prospective authors are invited to submit original manuscripts on topics within this broad scope including, but not limited to:

  • Information theoretic methods for deep learning
  • Robustness for training and inference
  • Understanding generalization in over-parametrized models
  • Efficient and compressed model representations
  • Deep generative models and inverse problems
  • Large-scale efficient training of large models
  • Non-convex optimization in deep learning
  • Deep learning for source and channel coding

Guest Editors

Lead Guest Editor: Alex Dimakis: dimakis@austin.utexas.edu
Richard Baraniuk:
Sewoong Oh: sewoong@cs.washington.edu
Nati Srebro: nati@ttic.edu
Rebecca Willett: willett@uchicago.edu

Submission Guidelines

Prospective authors must follow the IEEE Journal on Selected Areas in Information Theory guidelines regarding the manuscript and its format. For details and templates, please refer to the IEEE Journal on Selected Areas in Information Theory Author Information webpage. All papers should be submitted through Scholar One according to the schedule below.

Important Dates

Manuscript Due: 1 October 2019
Acceptance Notification: 15 March 2020
Final to Publisher: 5 April 2020
Expected Publication: April/May 2020