Recursive Binding for Similarity-Preserving Hypervector Representations of Sequences
This work addresses a critical step in hyperdimensional computing for AI and cognitive computing, offering a method for sequence representation that is incremental in improving similarity preservation and shift equivariance.
The paper tackles the problem of transforming sequences into hyperdimensional vector representations that preserve similarity of identical elements at nearby positions and are equivariant to sequence shifts, using recursive binding and superposition operations. The results show performance on par with more sophisticated approaches in experiments with symbolic strings modeling human word similarity.
Hyperdimensional computing (HDC), also known as vector symbolic architectures (VSA), is a computing framework used within artificial intelligence and cognitive computing that operates with distributed vector representations of large fixed dimensionality. A critical step for designing the HDC/VSA solutions is to obtain such representations from the input data. Here, we focus on sequences and propose their transformation to distributed representations that both preserve the similarity of identical sequence elements at nearby positions and are equivariant to the sequence shift. These properties are enabled by forming representations of sequence positions using recursive binding and superposition operations. The proposed transformation was experimentally investigated with symbolic strings used for modeling human perception of word similarity. The obtained results are on a par with more sophisticated approaches from the literature. The proposed transformation was designed for the HDC/VSA model known as Fourier Holographic Reduced Representations. However, it can be adapted to some other HDC/VSA models.