Channel Estimation – Machine learning applied to the physical layer of millimeter – Wave MIMO systems
Channel estimation is challenging in millimeter wave systems because it combines both analog and digital beam forming (called the hybrid architecture). The objective of this challenge is to present solutions to the site-specific channel estimation problem with hybrid architectures. This talk will address the challenges of the problem as well as state-of-the-art solutions. Participants will be encouraged to design either a ML-based approach or a more conventional signal processing algorithm that can learn some priors from the provided training data set to provide high accuracy channel estimates with low training overhead during the testing phase. Furthermore, a description of the datasets for training and testing which is obtained from a specific urban location, and thus being site-specific will be provided. Finally, a description of the technical goals of this challenge will be provided. This will give insights into the trade-offs between data-driven and model-driven algorithms.