Project: EDL P16-25-P7
Project title: Efficient Deep Learning Platforms (eDLP)
Project leader: Sander Stuijk, TU Eindhoven (TU/e)
Co-applicant(s): Marco Bekooij (UT), Dr. Sander Bohte (CWI), Prof.dr. Jose Pineda de Gyvez (TU/e), Guido Dolmans (TU/e), Prof.dr. Henk Corporaal (TU/e)
Partners: HOLST, NXP, Intel, CWI, Donders Institute, NVIDIA, TU Dresden.
Short description: HW-SW design for efficient processing of DNNs low energy embedded systems high performance
P7 addresses three main energy-efficient related data efficient DL challenges:

  • definition of novel energy-efficient hardware platforms for state-of-the-art DL interference algorithms.
  • development of techniques for mapping of state-of-the-art DL algorithms to these hardware platforms.
  • definition of hardware/software provisions for in-field learning and model updates.