The Chair of Electronic Design Automation at TUM (TUM-EDA) currently offers two open PhD positions
1. Open PhD Position for Machine Learning for Electronic Design Automation
Expected starting date: June 01, 2022 - March 01, 2023
Duration: 3 years with a possible extension
TUM-EDA offers a new PhD candidate position in the area of Machine Learning for Electronic Design Automation. Currently, we are conducting research on extensive topics covering design methodologies of integrated circuits, hardware acceleration of neural networks, and efficient computing solutions based on emerging technologies. This new PhD position aims to explore the learning ability of neural networks and more generally machine learning algorithms to solve problems in designing large-scale integrated circuits. Concrete topics of this position can include but not limited to:
- Circuit structure learning and generation using neural networks;
- Machine learning for logic synthesis;
- Convolutional and graph neural networks for timing analysis and optimization.
The potential candidate should be familiar with integrated circuits and its design flow. In addition, the candidate should have a good understanding of neural networks or is strongly interested in exploring machine learning methods.
If you are interested in this PhD position, please contact Dr.-Ing. Li Zhang (grace-li.zhang@tum.de) with your CV and transcripts.
2. Open PhD Position for Efficient and Robust Optical Accelerators for Neural Networks
Expected starting date: June 01, 2022 - January 01, 2023
Duration: 3 years with a possible extension
In recent years, deep neural networks (DNNs) have achieved remarkable breakthroughs. This advance, however, is accompanied by a rapid increase of the number of network layers and computation operations in DNNs. To overcome the bottleneck of computational performance, optical multiply-and-accumulate (OMAC) modules based on silicon-photonic components have been implemented as optical accelerators for neural networks with light as the computation media. Existing research on OMAC design, however, is still restricted to accelerating neural networks of small sizes and simple structures, and thus of limited computational capability. Solutions to address the challenges from efficiency to robustness in applying OMAC modules to accelerate large neural networks are still missing. In this project, we aim to investigate the systematic design of neural network acceleration with optical components to enhance hardware efficiency, computation accuracy, and robustness under hardware uncertainties.
The potential candidate should be familiar with neural networks and have a strong interest in their hardware acceleration. In addition, knowledge on optical components and connections is required.
If you are interested in this PhD position, please contact Dr.-Ing. Li Zhang (grace-li.zhang@tum.de) with your CV and transcripts.