Masoud Daneshtalab, Professor

Masoud Daneshtalab (http://www.idt.mdh.se/~md/) is currently a Professor at Mälardalen University (MDH) and leads the Heterogeneous System research group (www.es.mdh.se/hero/). He joined KTH as European Marie Curie Fellow in 2014. Before that, he was a university lecturer and group leader at University of Turku in Finland from 2012-2014.

He has represented Sweden in the management committee of the EU COST Actions IC1202: Timing Analysis on Code-Level (TACLe). Since 2016 he is in Euromicro board of Director and a member of the HiPEAC network.

His research interests include interconnection networks, hardware/software co-design, deep learning acceleration and evolutionary optimization. He has published 2 book, 8 book chapters, and over 200 refereed international journals and conference papers within H-index 28. He has served in Technical Program Committees of all major conferences in his area including DAC, NOCS, DATE, ASPDAC, ICCAD, HPCC, ReCoSoC, SBCCI, ESTIMedia, VLSI Design, ICA3PP, SOCC, VDAT, DSD, PDP, ICESS, Norchip, MCSoC, CADS, EUC, DTIS, NESEA, CASEMANS, NoCArc, MES, PACBB, MobileHealth, and JEC-ECC.

He has co-led several research projects including: SafeDeep, AutoDeep, DeepMaker, DESTINE, PROVIDENT, HERO, AGENT, CUBRIC, ERoT, and µBrain with a total estimation of 114 MSEK (11 MEuro).

  • Many-core Embedded Systems (resource management, scheduling, dark silicon, etc.)
  • Interconnection Networks (multicasting, QoS, learning-based and adaptive routing, etc)
  • Deep Learning (network architecture design and optimization of CNN, RNN, MLP, and SNN)
  • Reconfigurable Architecture (FPGA, DRRA, CGRA, etc.)
  • Multi-objective optimization (Ant colony, genetic, Q-learning, ICA, dynamic programming, etc.

[Show all publications]

[Google Scholar author page]

Latest publications:

NAS-PxAF: Neural Architecture Search for Accurate Detecting Paroxysmal Atrial Fibrillation (Nov 2022)
Mehdi Asadi , Mohammad Loni, Masoud Daneshtalab, Mikael Sjödin, Arash Ghareh Baghi
IEEE Transactions on Systems, Man, and Cybernetics: Systems (SMCS)

3DLaneNAS: Neural Architecture Search for Accurate and Light-Weight 3D Lane Detection (Sep 2022)
Ali Zoljodi, Mohammad Loni, Sadegh Abadijou , Mina Alibeigi , Masoud Daneshtalab
ICANN2022: 31st International Conference on Artificial Neural Networks (ICANN2022)

End-to-end Timing Model Extraction from TSN-Aware Distributed Vehicle Software (Aug 2022)
Bahar Houtan, Mehmet Onur Aybek , Mohammad Ashjaei, Masoud Daneshtalab, Mikael Sjödin, Saad Mubeen
Euromicro Conference Series on Software Engineering and Advanced Applications (SEAA2022)

Towards a Predictable and Cognitive Edge-Cloud Architecture for Industrial Systems (Jul 2022)
Mohammad Ashjaei, Saad Mubeen, Masoud Daneshtalab, Victor Casamayor , Geoffrey Nelissen
Real-time And intelliGent Edge computing workshop (RAGE2022)

AVB-aware Routing and Scheduling for Critical Traffic in Time-sensitive Networks with Preemption (Jun 2022)
Aldin Berisa, Luxi Zhao , Silviu Craciunas , Mohammad Ashjaei, Saad Mubeen, Masoud Daneshtalab, Mikael Sjödin
The 30th International Conference on Real-Time Networks and Systems (RTNS'22)

FaCT-LSTM: Fast and Compact Ternary Architecture for LSTM Recurrent Neural Networks (Jun 2022)
Najmeh Nazari , Seyed Ahmad Mirsalari , Sima Sinaei, Mostafa Salehi , Masoud Daneshtalab
IEEE Design and Test (IEEE D&T)

MSc theses supervised (or examined):
Thesis TitleStatus
OBJECT RECOGNITION THROUGH DEEP CONVOLUTIONAL LEARNING FOR FPGA finished