Seyedhamidreza Mousavi, Doctoral student
I am currently a PhD student at Malardalan University advised by Masoud Daneshtalab.
My main interests lie in machine learning and computer vision. Right now, my research is focused on creating deep learning models that are both high-performing and compact, while also ensuring their safety.
I am also interested in the intersection of tiny deep neural networks and important factors like trustworthiness, adversarial attacks, reliability, and fairness. This means I study how deep learning models can be vulnerable to attacks and work on developing ways to make them more robust. Additionally, I am passionate about making sure that these models are fair in their decision-making processes.
My main interests lie in machine learning and computer vision. Right now, my research is focused on creating deep learning models that are both high-performing and compact, while also ensuring their safety.
I am also interested in the intersection of tiny deep neural networks and important factors like trustworthiness, adversarial attacks, reliability, and fairness. This means I study how deep learning models can be vulnerable to attacks and work on developing ways to make them more robust. Additionally, I am passionate about making sure that these models are fair in their decision-making processes.
Efficient On-device Transfer Learning using Activation Memory Reduction (Sep 2023) Amin Yoosefi , Seyedhamidreza Mousavi, Masoud Daneshtalab, Mehdi Kargahi International Conference on Fog and Mobile Edge Computing (FMEC)
DASS: Differentiable Architecture Search for Sparse Neural Networks (Sep 2023) Seyedhamidreza Mousavi, Mohammad Loni, Mina Alibeigi , Masoud Daneshtalab ACM Transactions on Embedded Computing Systems (TECS 2024)
DASS: Differentiable Architecture Search for Sparse Neural Networks (Sep 2023) Seyedhamidreza Mousavi, Mohammad Loni, Mina Alibeigi , Masoud Daneshtalab EMBEDDED SYSTEMS WEEK (ESWEEK 2023)
Stealthy Attack on Algorithmic-Protected DNNs via Smart Bit Flipping (Apr 2022) Seyedhamidreza Mousavi International Symposium on Quality Electronic Design (ISQED)
TAS:Ternarized Neural Architecture Search for Resource-Constrained Edge Devices (Mar 2022) Mohammad Loni, Seyedhamidreza Mousavi, Mohammad Riazati, Masoud Daneshtalab, Mikael Sjödin Design, Automation and Test in Europe Conference (DATE'22)
Aadam: A Fast, Accurate, and Versatile Aging-Aware Cell Library Delay Model using Feed-Forward Neural Network (Nov 2020) Seyedhamidreza Mousavi IEEE/ACM International Conference On Computer Aided Design (ICCAD 2020)