DistriHD: A Memory Efficient Distributed Binary Hyperdimensional Computing Architecture for Image Classification

Liang, Dehua; Shiomi, Junichiro; Miura, Noriyuki; Awano, Hiromitsu

doi:10.1109/asp-dac52403.2022.9712589

“…Random Fourier Features (RFF) are used by Yu et al (2022) for the encoding of the images resulting in 95.4% accuracy. Traditional NNs have also been combined with HDC resulting in accuracies of 92.72% (Duan et al, 2022b), 94.8% (Liang et al, 2022), and 96.71% (Ma and Jiao, 2022). Zou et al (2021b) report an accuracy of 97.5% by extending the HDC encoding framework with manifold learning.…”

Section: Analysis Of Resultsmentioning

confidence: 99%

An encoding framework for binarized images using hyperdimensional computing

Smets,

Van Leekwijck,

Tsang

et al. 2024

Front. Big Data

0

View full text Add to dashboard Cite

IntroductionHyperdimensional 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.MethodsThis 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.ResultsThe 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.DiscussionThese 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.

show abstract

“…Random Fourier Features (RFF) are used by Yu et al (2022) for the encoding of the images resulting in 95.4% accuracy. Traditional NNs have also been combined with HDC resulting in accuracies of 92.72% (Duan et al, 2022b), 94.8% (Liang et al, 2022), and 96.71% (Ma and Jiao, 2022). Zou et al (2021b) report an accuracy of 97.5% by extending the HDC encoding framework with manifold learning.…”

Section: Analysis Of Resultsmentioning

confidence: 99%

fdata-07-1371518-g0002.tif

0

View full text Add to dashboard Cite

“…Random Fourier Features (RFF) are used by Yu et al (2022) for the encoding of the images resulting in 95.4% accuracy. Traditional NNs have also been combined with HDC resulting in accuracies of 92.72% (Duan et al, 2022b), 94.8% (Liang et al, 2022), and 96.71% (Ma and Jiao, 2022). Zou et al (2021b) report an accuracy of 97.5% by extending the HDC encoding framework with manifold learning.…”

Section: Analysis Of Resultsmentioning

confidence: 99%

Data_Sheet_1.pdf

0

View full text Add to dashboard Cite

DistriHD: A Memory Efficient Distributed Binary Hyperdimensional Computing Architecture for Image Classification

Cited by 14 publications

References 11 publications

An encoding framework for binarized images using hyperdimensional computing

An encoding framework for binarized images using hyperdimensional computing

fdata-07-1371518-g0002.tif

Data_Sheet_1.pdf

Contact Info

Product

Resources

About