Hyperdimensional computing : a fast, robust, and interpretable paradigm for biological data
- Author
- Michiel Stock (UGent) , Wim Van Criekinge (UGent) , Dimitri Boeckaerts, Steff Taelman (UGent) , Maxime Van Haeverbeke (UGent) , Pieter Dewulf and Bernard De Baets (UGent)
- Organization
- Project
- Abstract
- Advances in bioinformatics are primarily due to new algorithms for processing diverse biological data sources. While sophisticated alignment algorithms have been pivotal in analyzing biological sequences, deep learning has substantially transformed bioinformatics, addressing sequence, structure, and functional analyses. However, these methods are incredibly data-hungry, compute-intensive, and hard to interpret. Hyperdimensional computing (HDC) has recently emerged as an exciting alternative. The key idea is that random vectors of high dimensionality can represent concepts such as sequence identity or phylogeny. These vectors can then be combined using simple operators for learning, reasoning, or querying by exploiting the peculiar properties of high-dimensional spaces. Our work reviews and explores HDC's potential for bioinformatics, emphasizing its efficiency, interpretability, and adeptness in handling multimodal and structured data. HDC holds great potential for various omics data searching, biosignal analysis, and health applications.
- Keywords
- DISTRIBUTED REPRESENTATIONS, CLASSIFICATION, PREDICTION, BINDING, MODELS
Downloads
-
journal.pcbi.1012426.pdf
- full text (Published version)
- |
- open access
- |
- |
- 1.24 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01J9TST6NF39EM0FHMKK9YZ1FT
- MLA
- Stock, Michiel, et al. “Hyperdimensional Computing : A Fast, Robust, and Interpretable Paradigm for Biological Data.” PLOS COMPUTATIONAL BIOLOGY, vol. 20, no. 9, 2024, doi:10.1371/journal.pcbi.1012426.
- APA
- Stock, M., Van Criekinge, W., Boeckaerts, D., Taelman, S., Van Haeverbeke, M., Dewulf, P., & De Baets, B. (2024). Hyperdimensional computing : a fast, robust, and interpretable paradigm for biological data. PLOS COMPUTATIONAL BIOLOGY, 20(9). https://doi.org/10.1371/journal.pcbi.1012426
- Chicago author-date
- Stock, Michiel, Wim Van Criekinge, Dimitri Boeckaerts, Steff Taelman, Maxime Van Haeverbeke, Pieter Dewulf, and Bernard De Baets. 2024. “Hyperdimensional Computing : A Fast, Robust, and Interpretable Paradigm for Biological Data.” PLOS COMPUTATIONAL BIOLOGY 20 (9). https://doi.org/10.1371/journal.pcbi.1012426.
- Chicago author-date (all authors)
- Stock, Michiel, Wim Van Criekinge, Dimitri Boeckaerts, Steff Taelman, Maxime Van Haeverbeke, Pieter Dewulf, and Bernard De Baets. 2024. “Hyperdimensional Computing : A Fast, Robust, and Interpretable Paradigm for Biological Data.” PLOS COMPUTATIONAL BIOLOGY 20 (9). doi:10.1371/journal.pcbi.1012426.
- Vancouver
- 1.Stock M, Van Criekinge W, Boeckaerts D, Taelman S, Van Haeverbeke M, Dewulf P, et al. Hyperdimensional computing : a fast, robust, and interpretable paradigm for biological data. PLOS COMPUTATIONAL BIOLOGY. 2024;20(9).
- IEEE
- [1]M. Stock et al., “Hyperdimensional computing : a fast, robust, and interpretable paradigm for biological data,” PLOS COMPUTATIONAL BIOLOGY, vol. 20, no. 9, 2024.
@article{01J9TST6NF39EM0FHMKK9YZ1FT,
abstract = {{Advances in bioinformatics are primarily due to new algorithms for processing diverse biological data sources. While sophisticated alignment algorithms have been pivotal in analyzing biological sequences, deep learning has substantially transformed bioinformatics, addressing sequence, structure, and functional analyses. However, these methods are incredibly data-hungry, compute-intensive, and hard to interpret. Hyperdimensional computing (HDC) has recently emerged as an exciting alternative. The key idea is that random vectors of high dimensionality can represent concepts such as sequence identity or phylogeny. These vectors can then be combined using simple operators for learning, reasoning, or querying by exploiting the peculiar properties of high-dimensional spaces. Our work reviews and explores HDC's potential for bioinformatics, emphasizing its efficiency, interpretability, and adeptness in handling multimodal and structured data. HDC holds great potential for various omics data searching, biosignal analysis, and health applications.}},
articleno = {{e1012426}},
author = {{Stock, Michiel and Van Criekinge, Wim and Boeckaerts, Dimitri and Taelman, Steff and Van Haeverbeke, Maxime and Dewulf, Pieter and De Baets, Bernard}},
issn = {{1553-734X}},
journal = {{PLOS COMPUTATIONAL BIOLOGY}},
keywords = {{DISTRIBUTED REPRESENTATIONS,CLASSIFICATION,PREDICTION,BINDING,MODELS}},
language = {{eng}},
number = {{9}},
pages = {{23}},
title = {{Hyperdimensional computing : a fast, robust, and interpretable paradigm for biological data}},
url = {{http://doi.org/10.1371/journal.pcbi.1012426}},
volume = {{20}},
year = {{2024}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: