| Project: |
EDL P16-25-P7 |
| Project title: |
Efficient Deep Learning Platforms (eDLP) |
| Project leader: |
Dr.ir. Sander Stuijk, TU Eindhoven (TU/e) |
| Co-applicant(s): |
Prof.dr.ir. Marco Bekooij (UT), Dr. Sander Bohte (CWI), Prof.dr. Jose Pineda de Gyvez (TU/e), Prof.dr.ir. 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.
|
