What can NVMs do for Neuromorphic Computational Systems - Prospects & Challenges




Abstract: In this paper, we review some recent advances in developing neuromorphic algorithms based on the operating principles of the brain and how NVMs could enable translating them into energy efficient hardware implementations. We will also present challenges associated with scaling such devices to enable artificial hardware that will operate at the same efficiency as the human brain.

Bio: Bipin Rajendran is an Associate Professor of Electrical Engineering at I.I.T. Bombay. His research focuses on developing algorithms, systems and devices for computing inspired by biology. He has contributed to more than 45 peer-reviewed conference and journal publications, 50 US patents and a book on Phase Change Memory. Earlier, he was a Research Staff Member at IBM Watson and an adjunct faculty at Columbia University. He obtained a Ph.D in Electrical Engineering from Stanford University.