Implementation of a hardware accelerator for neural networks for processing radar data
- Subject:Beschleuniger für KI-Algorithmen
- Type:Masterarbeit
- Date:ab 02 / 2023
- Tutor:
Implementation of a hardware accelerator for neural networks for processing radar data
Context
Artificial intelligence is used in numerous applications to process large amounts of data. In the automotive sector, the processing of radar data is becoming increasingly important and is considered crucial for the success of fully autonomous systems. In particular, sensor-related data pre-processing is subject to stringent latency and required area requirements.
Tasks
In this thesis an accelerator for neural networks for the processing of radar data shall be investigated. This accelerator shall be embedded in an existing vehicle system. In order to meet the requirements of the system, optimizations such as quantization, pruning, approximate computing or sparsity will be investigated. The accelerator shall be optimized with respect to latency and resource overhead.
Requirements
- Programming experience in Python and C++
- Basic knowledge of neural networks
- Motivation and interest in solving technical problems independently
- Basic knowledge about FPGAs is advantageous