A Caltech Library Service

DSP-Inspired Deep Learning: A Case Study Using Ramanujan Subspaces

Tenneti, Srikanth V. and Vaidyanathan, P. P. (2019) DSP-Inspired Deep Learning: A Case Study Using Ramanujan Subspaces. In: 2019 53rd Asilomar Conference on Signals, Systems, and Computers. IEEE , Piscataway, NJ, pp. 2072-2076. ISBN 9781728143002.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


Can Deep Learning be used to augment DSP techniques? Algorithms in DSP are typically developed starting from a mathematical model of an application. In some cases however, simplicity of the model can result in deterioration of performance when there is a severe modeling mis-match. This paper explores the idea of implementing a DSP technique as a computational graph, so that hundreds of parameters can jointly be trained to adapt to any given dataset. Using the specific example of period estimation by Ramanujan Subspaces, significant improvement in estimation accuracies under high noise and very short datalengths is demonstrated.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Tenneti, Srikanth V.0000-0002-5415-3681
Vaidyanathan, P. P.0000-0003-3003-7042
Additional Information:© 2019 IEEE. This work was supported in parts by the NSF grant CCF-1712633, the ONR grant N00014-18-1-2390, and an Amazon AI fellowship facilitated through IST, California Institute of Technology.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-18-1-2390
Subject Keywords:Ramanujan Sums, Ramanujan Subspaces, Deep Learning, Periodicity, Computational Graphs
Record Number:CaltechAUTHORS:20200403-143552815
Persistent URL:
Official Citation:S. V. Tenneti and P. P. Vaidyanathan, "DSP-Inspired Deep Learning: A Case Study Using Ramanujan Subspaces," 2019 53rd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2019, pp. 2072-2076; doi: 10.1109/ieeeconf44664.2019.9048783
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:102334
Deposited By: Tony Diaz
Deposited On:03 Apr 2020 22:08
Last Modified:16 Nov 2021 18:11

Repository Staff Only: item control page