Vector-Symbolic Architectures (a.k.a. Hyperdimensional Computing) is a relatively new computational paradigm that involves the use of random vectors in a high-dimensional space to represent and process information. As a computational paradigm, it finds applications in a wide range of fields, including artificial intelligence, natural language processing, internet-of-things, robotics, bioinformatics, and other scientific domains.

Here we are going to introduce some fundamental concepts at the base of Hyperdimensional Computing, following a presentation of hdlib, a library for building Vector-Symbolic Architectures with Python. Finally, we are going to see how to easily build a machine learning model based on the Hyperdimensional Computing paradigm as a practical use case.

As a reference, hdlib is open-source, it is available on GitHub at https://github.com/cumbof/hdlib, and it is published on the Journal of Open Source Software at https://doi.org/10.21105/joss.05704.