Neurally-Inspired Hyperdimensional Classification for Efficient and Robust Biosignal Processing

Ni, Yang; Lesica, Nicholas A.; Zeng, Fan‐Gang; Imani, Mohsen

doi:10.1145/3508352.3549477

Cited by 14 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few years, prior HDC research works have applied the brain-like functionalities of HDC to diverse applications, for example, outlier detection (Wang et al, 2022 ), biosignal processing (Rahimi et al, 2020 ; Ni et al, 2022c ; Pale et al, 2022 ), speech recognition (Hernandez-Cane et al, 2021 ), and gesture recognition (Rahimi et al, 2016 ). Apart from classification learning tasks, it has also been applied to genomic sequencing (Zou et al, 2022 ; Barkam et al, 2023b ), nonlinear regression (Hernández-Cano et al, 2021 ; Ni et al, 2023b ), reinforcement learning (Chen et al, 2022 ; Issa et al, 2022 ; Ni et al, 2022a , 2023a ), and graph reasoning (Poduval et al, 2022a ; Chen et al, 2023 ).…”

Section: Related Workmentioning

confidence: 99%

Hyperdimensional computing with holographic and adaptive encoder

Hernández-Cano,

Ni,

Zou

et al. 2024

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

IntroductionBrain-inspired computing has become an emerging field, where a growing number of works focus on developing algorithms that bring machine learning closer to human brains at the functional level. As one of the promising directions, Hyperdimensional Computing (HDC) is centered around the idea of having holographic and high-dimensional representation as the neural activities in our brains. Such representation is the fundamental enabler for the efficiency and robustness of HDC. However, existing HDC-based algorithms suffer from limitations within the encoder. To some extent, they all rely on manually selected encoders, meaning that the resulting representation is never adapted to the tasks at hand.MethodsIn this paper, we propose FLASH, a novel hyperdimensional learning method that incorporates an adaptive and learnable encoder design, aiming at better overall learning performance while maintaining good properties of HDC representation. Current HDC encoders leverage Random Fourier Features (RFF) for kernel correspondence and enable locality-preserving encoding. We propose to learn the encoder matrix distribution via gradient descent and effectively adapt the kernel for a more suitable HDC encoding.ResultsOur experiments on various regression datasets show that tuning the HDC encoder can significantly boost the accuracy, surpassing the current HDC-based algorithm and providing faster inference than other baselines, including RFF-based kernel ridge regression.DiscussionThe results indicate the importance of an adaptive encoder and customized high-dimensional representation in HDC.

show abstract