M. G. Sarwar Murshed
Ph.D. Student, Electrical and Computer Engineering
Clarkson University
Email: murshem (at) clarkson (dot) edu



My research focusses broadly on developing algorithms for efficient and scalable machine learning systems. I am particularly interested in efficient and hardware-friendly deep learning and its applications in biometrics, vision, language, and speech using the edge computing paradigm. I am excited about grounding my research in applications relating to accelerating science and engineering. My research is supported by Verizon and Badger Technologies. Prior to joining Clarkson University, I worked at Samsung R&D. I was working on Samsung IoT projects.

  • Deep Slap Fingerprint Segmentation for Juveniles and Adults
    M.G. Sarwar Murshed, Robert Kline, Keivan Bahmani, Faraz Hussain, Stephanie Schuckers
    2021 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)
    [doi] [arXiv]

  • Machine Learning at the Network Edge: A Survey
    M.G. Sarwar Murshed, Christopher Murphy, Daqing Hou, Nazar Khan, Ganesh Ananthanarayanan, Faraz Hussain
    ACM Computing Surveys 54, 8, Article 170 (October 2021)
    [doi] [arXiv]

  • Resource-aware On-device Deep Learning for Supermarket Hazard Detection
    M. G. Sarwar Murshed, James J. Carroll, Nazar Khan, Faraz Hussain
    19th IEEE International Conference on Machine Learning and Applications (ICMLA 2020)
    [doi]

  • Fast Resilient-Aware Data Layout Organization for Resistive Computing Systems
    Baogang Zhang ; M. G. Sarwar Murshed ; Faraz Hussain ; Rickard Ewetz
    2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)
    [conference link] [bib]

  • FlexServe: Deployment of PyTorch Models as Flexible REST Endpoints
    Edward Verenich, Alvaro Velasquez, M.G. Sarwar Murshed, Faraz Hussain
    2020 USENIX Conference on Operational Machine Learning (OpML 2020)
    [conference link] [preprint-pdf] [bib]

  • Hazard Detection in Supermarkets using Deep Learning on the Edge
    M.G. Sarwar Murshed, Edward Verenich, Conrad Gende, James J. Carroll, Nazar Khan, Faraz Hussain
    3rd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 2020) [poster]
    [conference link] [pdf] [bib]

  • Hazard Detection in Supermarkets using Deep Learning on the Edge
    M.G. Sarwar Murshed, Edward Verenich, James J. Carroll, Nazar Khan, Faraz Hussain
    [arXiv]

  • The Utility of Feature Reuse: Transfer Learning in Data-Starved Regimes
    Edward Verenich, Alvaro Velasquez, M.G. Sarwar Murshed, Faraz Hussain
    [arXiv] [bib]