Fachgebiet Entwurf Mikroelektronischer Systeme (EMS)

Muhammad Mohsin Ghaffar, M.Sc.


Anschrift

Erwin-Schrödinger-Straße
Gebäude 12, Raum 264
67663 Kaiserslautern

Kontakt

Telefon: (+49) 631 / 205-3354
Fax: (+49) 631 / 205-4437
Email: ghaffar(at)eit.uni-kl.de

Forschungsgebiete

  • 3D-DRAM Integration
  • DRAM Architekturen
  • Memory Controller

Publikationen

QuantYOLO: A High-Throughput and Power-Efficient Object Detection Network for Resource and Power Constrained UAVs
M. G. Javed, M. Raza, M. M. Ghaffar , C. Weis, F. Shafait, N. Wehn , M. Shahzad. Accepted for publication, IEEE International Conference on Digital Image Computing: Techniques and Applications (DICTA2021), November, 2021, Gold Coast, QLD, Australia.

Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning
N. Abid, M. I. Malik, M. Shahzad, F. Shafait, H. Ali, M. M. Ghaffar, C. Weis, N. Wehn. Accepted for publication, IEEE International Conference on Digital Image Computing: Techniques and Applications (DICTA2021), November, 2021, Gold Coast, QLD, Australia.

iDocChip: A Configurable Hardware Accelerator for an End-to-End Historical Document Image Processing
M. Tekleyohannes, V. Rybalkin, M. M. Ghaffar, J. Varela, N. Wehn, A. Dengel. Accepted for publication, MDPI Journal of Imaging, Special Issue: Image Processing Using FPGAs, 2021.

When massive GPU parallelism ain't enough: A Novel Hardware Architecture of 2D-LSTM Neural Network
V. Rybalkin, J. Ney, M. Tekleyohannes, M. M. Ghaffar, N. Wehn. Accepted for publication, ACM Journal Transactions on Reconfigurable Technology and Systems (TRETS), 2021.

AI-ForestWatch: Semantic Segmentation based End-to-End Framework for Forest Estimation and Change Detection Using Multi-Spectral Remote Sensing Imagery
A. Zulfiqar, M. M. Ghaffar, M. Shahzad, C. Weis, M. I. Malik, F. Shafait, N. Wehn. Journal of Applied Remote Sensing, Volume 15, Issue 2, 2021.
Link

iDocChip - A Configurable Hardware Architecture for Historical Document Image Processing: Multiresolution Morphology-based Text and Image Segmentation
M. Tekleyohannes, V. Rybalkin, M. M. Ghaffar, J. Varela, N. Wehn, A. Dengel.International Journal of Parallel Programming, Springer, 2021.
Link

An Energy Efficient 3D-Heterogeneous Main Memory Architecture for Mobile Devices
D. M. Mathew, F. S. Prado, É. F. Zulian, C. Weis, M. M. Ghaffar, M. Jung, N. Wehn. ACM/IEEE International Symposium on Memory Systems (MEMSYS 2020), October, 2020, virtual conference.

An In-DRAM Architecture for Quantized CNNs using Fast Winograd Convolutions
M. M. Ghaffar, C. Sudarshan, C. Weis, M. Jung, N. Wehn. ACM/IEEE International Symposium on Memory Systems (MEMSYS 2020), October, 2020, virtual conference.

iDocChip - A Configurable Hardware Architecture for Historical Document Image Processing: Text Line Extraction
M. Tekleyohannes, V. Rybalkin, S. S. Bukhari, M. M. Ghaffar, N. Wehn and A. Dengel. International Conference on Reconfigurable Computing and FPGAs (ReConFig 2019), December, 2019, Cancun, Mexico.

iDocChip - A Configurable Hardware Architecture for Historical Document Image Processing: Multiresolution Morphology-based Text and Image Segmentation
M. Tekleyohannes, V. Rybalkin, S. Bukhari, M. M. Ghaffar, J. Varela, N. Wehn, A. Dengel. International Embedded Systems Symposium (IESS 2019), September, 2019, Friedrichshafen, Germany.
Best Paper Award

Fast Simulation of DRAMs with Neural Networks
M. Jung, J. Feldmann, M. M. Ghaffar, N. Wehn. Talk at the 1st ACM/IEEE Workshop on Machine Learning for CAD (MLCAD), September, 2019, Canmore, Alberta, Canada.

An In-DRAM Neural Network Processing Engine
C. Sudarshan, J. Lappas, M. M. Ghaffar, V. Rybalkin, C. Weis, M. Jung, N. Wehn. IEEE International Symposium on Circuits and Systems (ISCAS), May, 2019, Sapporo, Japan.

FINN-L: Library Extensions and Design Trade-off Analysis for Variable Precision LSTM Networks on FPGAs
V. Rybalkin, A. Pappalardo, M. M. Ghaffar, G. Gambardella, N. Wehn, M. Blott. 28th International Conference on Field Programmable Logic and Applications (FPL), August, 2018, Dublin, Ireland.

iDocChip: A Configurable Hardware Architecture for Historical Document Image Processing: Percentile Based Binarization
V. Rybalkin, S. S. Bukhari, A. Ghafoor, M. M. Ghaffar, N. Wehn, A. Dengel. ACM DocEng 2018 Conference, August, 2018, Halifax, Nova Scotia, Canada.

Zum Seitenanfang