R
Rathinakumar Appuswamy
Researcher at IBM
Publications - 52
Citations - 5824
Rathinakumar Appuswamy is an academic researcher from IBM. The author has contributed to research in topics: Linear network coding & TrueNorth. The author has an hindex of 18, co-authored 51 publications receiving 4506 citations. Previous affiliations of Rathinakumar Appuswamy include Indian Institute of Technology Kanpur & University of California, San Diego.
Papers
More filters
Proceedings ArticleDOI
Network coding for computing
TL;DR: A generalized min-cut upper bound is given for the network computation problem of a set of source nodes in an acyclic network and a single receiver node computes a function f of the messages to characterize the maximum number of times f can be computed per network usage.
Proceedings ArticleDOI
Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Inference
Jeffrey L. McKinstry,Steven K. Esser,Rathinakumar Appuswamy,Deepika Bablani,John V. Arthur,Izzet B. Yildiz,Dharmendra S. Modha +6 more
TL;DR: In this paper, the authors propose to reduce the solution distance by starting with pretrained fp32 baseline networks, and combat noise introduced by quantizing weights and activations during training by training longer and reducing learning rates.
Proceedings ArticleDOI
Network computing capacity for the reverse butterfly network
TL;DR: The maximum rate at which the message sum can be computed at the receiver is characterized and it is demonstrated that linear coding is suboptimal.
Journal ArticleDOI
Time and Energy Complexity of Function Computation Over Networks
TL;DR: This paper considers a model where links are interference and noise-free, suitable for modeling wired networks, and extends results on symmetric functions to general network topologies, and obtains a corollary that answers an open question about the computation of the parity function over ring and tree networks.
Journal ArticleDOI
Visual saliency on networks of neurosynaptic cores
Alexander Andreopoulos,Brian Taba,Andrew S. Cassidy,Alvarez-Icaza Rivera Rodrigo,Myron D. Flickner,William P. Risk,Arnon Amir,Paul A. Merolla,John V. Arthur,David Berg,Jeffrey A. Kusnitz,Pallab Datta,Steve K. Esser,Rathinakumar Appuswamy,Dharmendra S. Modha +14 more
TL;DR: A bottom-up model of visual saliency, inspired by the primate visual cortex, is proposed, compatible with TrueNorth-a low-power, brain-inspired neuromorphic substrate that runs large-scale spiking neural networks in real-time.