Fig 1.
(a) The hallmarks of HDC. HVs work reliably due to their large dimensionality N (i.e., the Law of Large Numbers states that component-wise properties SN, such as the fraction of positive components, converge to their expected value for large N), and the space is very homogeneous (e.g., most HVs are approximately equidistant). The information about an object is encoded holographically, and the information is robust to random errors. (b) Overview of the elementary operations of HDC: generating, bundling, binding, and permuting. (c) Similarity is computed based on component-wise comparisons. (d) General HDC workflow, based on Thomas, Dasgupta, and Rosing [32], where red boxes indicate the data space and blue boxes indicate operations in the hyperdimensional space.
Fig 2.
Opportunities for bioinformatics.
(i) HDC is computationally efficient because it can usually be done using simple bit or arithmetic operations; (ii) it is explainable because of its reversibility; (iii) it can easily combine different types of data sources; and (iv) it can represent complex, structured, and hierarchical information.