An encoding framework for binarized images using hyperdimensional computing.
| Autor: | Smets L; IDLab, Department of Computer Science, University of Antwerp-imec, Antwerp, Belgium., Van Leekwijck W; IDLab, Department of Computer Science, University of Antwerp-imec, Antwerp, Belgium., Tsang IJ; IDLab, Department of Computer Science, University of Antwerp-imec, Antwerp, Belgium., Latré S; IDLab, Department of Computer Science, University of Antwerp-imec, Antwerp, Belgium. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Frontiers in big data [Front Big Data] 2024 Jun 14; Vol. 7, pp. 1371518. Date of Electronic Publication: 2024 Jun 14 (Print Publication: 2024). |
| DOI: | 10.3389/fdata.2024.1371518 |
| Abstrakt: | Introduction: Hyperdimensional Computing (HDC) is a brain-inspired and lightweight machine learning method. It has received significant attention in the literature as a candidate to be applied in the wearable Internet of Things, near-sensor artificial intelligence applications, and on-device processing. HDC is computationally less complex than traditional deep learning algorithms and typically achieves moderate to good classification performance. A key aspect that determines the performance of HDC is encoding the input data to the hyperdimensional (HD) space. Methods: This article proposes a novel lightweight approach relying only on native HD arithmetic vector operations to encode binarized images that preserves the similarity of patterns at nearby locations by using point of interest selection and local linear mapping . Results: The method reaches an accuracy of 97.92% on the test set for the MNIST data set and 84.62% for the Fashion-MNIST data set. Discussion: These results outperform other studies using native HDC with different encoding approaches and are on par with more complex hybrid HDC models and lightweight binarized neural networks. The proposed encoding approach also demonstrates higher robustness to noise and blur compared to the baseline encoding. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2024 Smets, Van Leekwijck, Tsang and Latré.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|