back to list
Project: NXP: Automatic joint design and optimization of neural networks
Description
- Automatic joint design and optimization of neural networks
- Neural Networks can be made more efficient and more accurate through a wide variety of techniques (Neural Architecture Search, Quantization, Pruning, …), but it is an open question on how and when to leverage these techniques in combination.
- Hence, this project will investigate the integration of orthogonal optimization techniques. We select a subset of techniques to enable and explore based on interest, applicability and feasibility, the scope of which can be extended gradually where possible and relevant, e.g.:
- How to decide the number of clusters for weight clustering in a NAS setup?
- For early exit networks: how to identify optimal exit points through NAS?
- How to decide on the optimal rank to leverage low-rank matrix decomposition?
- How to exploit data-free optimization and in which stage of the full pipeline?
Contact the TU/e supervisor (Joaquin Vanschoren). Please note that final acceptance will depend on the availability of supervision bandwidth and daily supervision at TU/e, as well as NXP.
Details
- Supervisor
-
Joaquin Vanschoren
- External location
- NXP
- Interested?
-
Get in contact