Over the years, a number of EDA tools have been reported to automate the design of ΣΔMs, mostly focused on optimizing system-level tasks - such as architecture selec-tion, loop-filter design, behavioral modeling, simulation and sizing, as well as electri-cal design and validation. Recent works demonstrate that Artificial Intelligence (AI) algorithms can be applied to automate analog circuit design. Their use in ΣΔMs has been also applied to improve the performance metrics of ΣΔMs and ADCs by means of linearization or calibration techniques based on Artificial Neural Networks (ANNs). Some authors have proposed using ANNs in an optimization-based synthesis meth-odology. In some of them, the ANN has been trained to replace the simulator, while other approaches consider ANNs as an optimization engine.
The idea of this thesis is to investigate an ANN-based performance prediction and optimization methodology for the automated high-level design of ΣΔMs.
What we expect:
- Basic understanding of ADCs
- Experience in Python
- Organized and well documented research and dedication to successful work