Artificial Neural Networks (ANNs) form the main approach in Artificial Intelligence (AI). They have two major drawbacks, however: (1) ANNs require significant computational resources; (2) they lack transparency. These challenges restrict the widespread application of AI in daily life. The required resources prevent the use of ANNs on resource-constrained devices and the lack of transparency limits their adoption in many areas where transparency is critical. This action will address these challenges via development of Vector Symbolic Architectures (VSAs): a transparent, bio-inspired framework for AI. With respect to the 1st challenge, VSAs have the potential to become a computational paradigm for emerging low-power computing hardware with huge potential for implementing AI algorithms. With respect to the 2nd challenge, VSAs are a promising framework for opening the black box of ANNs due to their predictable statistical properties. It is expected that VSAs will allow analytical characterization of a class of Recurrent ANNs. The overall research aim of this action is to improve the understanding of computing principles in high-dimensional spaces with VSAs, and to advance the theory and design principles of simple AI algorithms implementable on emerging low-power computing hardware. The research aim comprises five research objectives. These are relevant to H2020 Work Programme since this action has much potential with respect to the “market creating innovation” and “digitising and transforming industry” aspects of the Programme. The mechanisms for achieving the objectives include both theoretical development and applied investigations. The methodological approach combines the current skills of the applicant with those acquired during this action. The applicant will develop VSAs skills to qualitatively higher level while working under the supervision of eminent researchers. This will enhance applicant’s professional maturity and prepare him for an independent career.