A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges

This is Part II of the two-part comprehensive survey devoted to a computing framework most commonly known under names Hyperdimensional Computing and Vector Symbolic Architectures (HDC/VSA). Both refer family computational models that use high-dimensional distributed representations rely on algebraic properties their key operations incorporate advantages structured symbolic vector representations. Holographic Reduced Representations [ 321 , 326 ] an influential HDC/VSA model well in machine learning domain often used whole family. However, for sake consistency, we field. I this 222 covered foundational aspects field, such as historical context leading development HDC/VSA, elements any model, models, transformation input data various types into vectors suitable HDC/VSA. second part surveys existing applications, role cognitive architectures, directions future work. Most applications lie within Machine Learning/Artificial Intelligence domain; however, also cover other provide complete picture. The written be useful both newcomers practitioners.