Biswajit Ray

Profile Information
Name
Dr. Biswajit Ray
Institution
University of Alabama
Position
Assistant Professor
Affiliation
University of Alabama in Huntsville
h-Index
14
ORCID
0000-0002-5890-1368
Biography
<p style="text-align: justify"><span style="font-family: &quot;Times New Roman&quot;, serif">Biswajit Ray is an Assistant Professor of Electrical and Computer Engineering with the University of Alabama in Huntsville, AL, USA, where he leads the Hardware Reliability Lab. Dr. Ray received Ph.D. from Purdue University, West Lafayette, IN in 2013 and then he worked in SanDisk Corporation, California, USA, developing 3D NAND flash memory technology.</span><span style="font-family: &quot;Times New Roman&quot;, serif"> </span><span style="font-family: &quot;Times New Roman&quot;, serif">His current research spans the boundaries of electron devices and systems</span><span style="font-family: &quot;Times New Roman&quot;, serif"> for addressing the challenges in hardware security and reliability. </span><span style="font-family: &quot;Times New Roman&quot;, serif">Dr. Ray has 10 U.S. issued patents on non-volatile memory systems, published more than 40 research papers in international journals and conferences. He is a permanent resident of USA.</span></p>
Publications:
"Gamma Ray Induced Error Pattern Analysis for MLC 3-D NAND Flash Memories" Biswajit Ray, IEEE Transactions on Nuclear Science Vol. 2021 Link
"Layer Dependent Bit Error Variation in 3-D NAND Flash Under Ionizing Radiation" Biswajit Ray, IEEE Transactions on Nuclear Science Vol. 67 2020 2021-2027 Link
"Radiation Induced Error Mitigation by Read-Retry Technique for MLC 3-D NAND Flash Memory" Biswajit Ray, IEEE Transactions on Nuclear Science Vol. 2021 Link
"Radiation Tolerance of 3-D NAND Flash Based Neuromorphic Computing System" Biswajit Ray, Proc. of the 2020 IEEE International Reliability Physics Symposium, Monterey, CA Vol. 2020 Link
In this paper we show the effectiveness of a multi-level-cell 3-D NAND flash chip as a weight storage device for a neuromorphic computing system under radiation environment. We find that the error-correction codes can be avoided for storing model weights in 3-D NAND for enabling low-power computing applications without sacrificing much accuracy (radiation dose <10k rad). Additionally, radiation induced BER data shows layer-to-layer variations, which can be utilized in favor of improving neural network’s accuracy.
Presentations:
"Word Line Dependent Bit Error in 3-D NAND Flash Under Ionizing Radiation" Biswajit Ray, IEEE Nuclear and Space Radiation Effects Conference July 2-3, (2019)
NSUF Articles:
RTE 2nd Call Awards Announced - Projects total approximately $1.6 million These project awards went to principal investigators from 26 U.S. universities, eight national laboratories, two British universities, and one Canadian laboratory. Tuesday, May 14, 2019 - Calls and Awards
DOE Awards 37 RTE Proposals - Awarded projects total nearly $1.4M in access awards Tuesday, July 14, 2020 - News Release, Calls and Awards
NSUF awards 30 Rapid Turnaround Experiment proposals - Approximately $1.53M has been awarded. Tuesday, June 14, 2022 - Calls and Awards
NSUF awards 22 Rapid Turnaround Experiment proposals - Thursday, September 14, 2023 - Calls and Awards