Open positions
Neural Architecture Search framework for efficient and reliable hybrid CNN-Transformer models for Edge AI
The PhD project aims to develop a neural architecture search (NAS) framework for designing an efficient, robust, and reliable hybrid CNN-Transformer supernetwork capable of generating distinct subnetworks specialised for various HW platforms without extensive retraining. The research objectives include: a) investigating existing and introducing novel training algorithms to enhance the robustness, reliability, and accuracy of the subnetworks within the supernetwork; b) developing fast and efficient search engine algorithms for extracting subnetworks from the trained supernetwork; c) training surrogate predictor models to evaluate key metrics such as accuracy, robustness, reliability, and latency for full-precision and quantised sub-networks. This PhD position is one of the 17 positions in the European Marie Skłodowska-Curie Action Doctoral network "TIRAMISU - Training and Innovation in Reliable and Efficient Chip Design for Edge AI" (2024-2028).
| Research field: |
Information and communication technology |
|---|---|
| Supervisors: |
Prof. Dr. Maksim Jenihhin Masoud Daneshtalab Prof. Dr. Wolfgang Ecker |
| Availability: | This position is available. |
| Offered by: |
Tallinn University of Technology School of Information Technologies |
| Application deadline: | Applications are accepted between January 22, 2025 00:00 and February 28, 2025 23:59 (Europe/Zurich) |