Assistant Professor
Computer Science and Engineering
360 Avery HallLincoln, NE 68588
(402) 472-5075
aroohi@unl.edu
Education
- Ph.D. in Computer Engineering, University of Central Florida (2019)
- M.Sc. in Computer Architecture, Science and Research Branch, Azad University, Tehran, Iran (2011)
- B.Sc. in Computer Engineering, Shiraz University, Shiraz, Iran (2008)
Research Interests
- Energy Efficient and High Performance Processing in-Memory Circuit, Architecture and Algorithm
- Brain-Inspired Computing, Neuromorphic Computing, Machine Learning Acceleration
- Secure Computation including , Hardware Security and Security of Artificial Intelligence
- Reconfigurable and Adaptive Computer Architectures
Recent Publications
- Processing-in-Memory Acceleration of MAC-based Applications Using Residue Number System: A
Comparative Study
Shaahin Angizi, Arman Roohi, MohammadReza Taheri, Deliang Fan
31st ACM Great Lakes Symposium on VLSI (GLSVLSI 2021), June 22-25, 2021
Publication year: 2021 -
Entropy-Based Modeling for Estimating Adversarial Bit-flip Attack Impact on
Binarized Neural Network
Navud Khoshavi, Saman Sargolzaei, Yu Bi, A. Roohi
26th Asia and South Pacific Design Automation Conference (ASP-DAC), Jan.18-21
Publication year: 2021 -
SHIELDeNN:
Online Accelerated Framework for Fault-Tolerant Deep Neural Network Architectures
Navid Khoshavi, Arman Roohi, Connor Broyles, Saman Sargolzaei, Yu Bi, David Z. Pan
57th Design Automation Conference (DAC), San Francisco, CA, USA, July 19-23
Publication year: 2020 -
Normally-Off
Computing Design Methodology Using Spintronics: From Devices to Architectures
Arman Roohi
International Green and Sustainable Computing Conference, October 19-22
Publication year: 2020 -
Hardware-assisted Black-box Adversarial Attack Evaluation Framework on Binarized Neural
Network
Navid Khoshavi, Arman Roohi, Yu Bi
41st IEEE Symposium on Security and Privacy
Publication year: 2020 -
Fiji-FIN: A
Fault Injection Framework on Quantized Neural Network Inference Accelerator
Navid Khoshavi, Connor Broyles, Yu Bi, Arman Roohi
IEEE International Conference on Machine Learning and Applications (ICMLA), October 19-22
Publication year: 2020 -
Entropy-Based Modeling for Estimating
Soft Errors Impact on Binarized Neural Network Inference
Navid Khoshavi, Saman Sargolzaei, Arman Roohi, Connor Broyles, Yu Bi
arXiv preprint
Publication year: 2020 -
Processing-In-Memory Acceleration of Convolutional Neural Networks for
Energy-Efficiency, and Power-Intermittency Resilience
Arman Roohi, Shaahin Angizi, Deliang Fan, Ronald F DeMara
20th International Symposium on Quality Electronic Design (ISQED), Santa Clara, CA, USA, 2019, pp. 8-13.
Publication year: 2019 -
PARC: A Novel
Design Methodology for Power Analysis Resilient Circuits using Spintronics
Arman Roohi, , and Ronald F. DeMara.
IEEE Transactions on Nanotechnology, vol. 18, pp. 885-889, 2019
Publication year: 2019 -
IRC: Cross-layer
design exploration of Intermittent Robust Computation units for IoTs
Arman Roohi, Ronald F DeMara
IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Miami, FL, USA, 2019, pp. 354-359.
Publication year: 2019 -
ApGAN:
Approximate GAN for Robust Low-Energy Learning from Imprecise Components
Arman Roohi, Shadi Sheikhfaal, Shaahin Angizi, Deliang Fan, and Ronald F. DeMara
IEEE Transactions on Computers, vol. 69, no. 3, pp. 349-360, 1 March 2020.
Publication year: 2019 -
Synthesis of
Normally-Off Boolean Circuits: An Evolutionary Optimization Approach Utilizing Spintronic
Devices
Arman Roohi, Ramtin Zand, Ronald F DeMara
19th International Symposium on Quality Electronic Design (ISQED), Santa Clara, CA, 2018, pp. 49-54.
Publication year: 2018 -
NV-Clustering:
Normally-Off Computing Using Non-Volatile Datapaths
Arman Roohi, Ronald F DeMara
IEEE Transactions on Computers, vol. 67, no. 7, pp. 949-959, 1 July 2018
Publication year: 2018