This direction focuses on developing AI-based processing methods and techniques for signals and images as the first step toward providing end-to-end AI solutions for various applications of signal processing. Analysis of multi-modal signals will gain the understanding of the entire complex systems, rather than analysis of each data separately. It requires an efficient and novel tool for analysis of such complex systems, which integrates multiple data and knowledge representing the same real world object into a consistent, accurate and useful representation. Deep neural networks and tensor networks, focusing on the networks' stability and sensitivity, decode imagined or executed tasks from raw EEG with additional synchronized physiological and behavioral data, will be also investigated.