GrapHD: Graph-Based Hyperdimensional Memorization for Brain-Like Cognitive Learning

Poduval, Prathyush; Alimohamadi, Haleh; Zakeri, Ali; Imani, Farhad; Najafi, M. Hassan; Givargis, Tony; Imani, Mohsen

doi:10.3389/fnins.2022.757125

Cited by 32 publications

(11 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, hypervector representation is (1) holographic , that information is distributed evenly across components of the hypervector (Kleyko et al, 2023 ), (2) robust , that hypervectors are extremely noise tolerant as a natural result of hypervector redundancy (Kanerva, 2009 ; Poduval et al, 2022b ; Barkam et al, 2023a ), and (3) simple , that only lightweight operations are needed to perform learning tasks (Hernandez-Cane et al, 2021 ; Ni et al, 2022b ). In addition, the ability for hypervectors to operate symbolically through simple arithmetic has granted HDC the ability to perform cognitive tasks in a transparent and compositional way, e.g., memorization, learning, and association (Poduval et al, 2022a ; Hersche et al, 2023 ). Given the importance of the properties aforementioned, most HDC frameworks have a dedicated and specially designed HDC encoder for mapping original inputs to corresponding hypervectors.…”

Section: Introductionmentioning

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

Section: Introductionmentioning

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

show abstract

“…We exploit Hyper-Dimensional Computing (HDC) as an alternative computational model that mimics important brain functionalities toward high-efficiency and noise-tolerant computation (Kanerva, 2009 ; Rahimi et al, 2016b ; Pale et al, 2021 , 2022 ; Zou et al, 2021 ). HDC supports operators that emulate the behavior of associative memory and enables higher cognitive functionalities (Gayler, 2004 ; Kanerva, 2009 ; Poduval et al, 2022 ). In HDC, objects are thereby encoded with high-dimensional vectors, called hypervectors , which have thousands of elements (Kanerva, 2009 ; Rahimi et al, 2016b ; Imani et al, 2019c ).…”

Section: Introductionmentioning

confidence: 99%

EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor

et al. 2022

Self Cite

View full text Add to dashboard Cite

Brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Hyper-Dimensional Computing (HDC) has shown promising results in enabling efficient and robust cognitive learning. In this study, we exploit HDC as an alternative computational model that mimics important brain functionalities toward high-efficiency and noise-tolerant neuromorphic computing. We present EventHD, an end-to-end learning framework based on HDC for robust, efficient learning from neuromorphic sensors. We first introduce a spatial and temporal encoding scheme to map event-based neuromorphic data into high-dimensional space. Then, we leverage HDC mathematics to support learning and cognitive tasks over encoded data, such as information association and memorization. EventHD also provides a notion of confidence for each prediction, thus enabling self-learning from unlabeled data. We evaluate EventHD efficiency over data collected from Dynamic Vision Sensor (DVS) sensors. Our results indicate that EventHD can provide online learning and cognitive support while operating over raw DVS data without using the costly preprocessing step. In terms of efficiency, EventHD provides 14.2× faster and 19.8× higher energy efficiency than state-of-the-art learning algorithms while improving the computational robustness by 5.9×.

show abstract

“…This encoding is performed using a set of pre-generated base vectors . HDC is well suited to address several learning tasks in IoT systems as: (i) HDC is computationally efficient and amenable to hardware level optimization 30 – 32 , (ii) it supports single-pass training with no back-propagation or gradient computation, (iii) HDC offers an intuitive and human-interpretable model 33 , (iv) it is a computational paradigm that can be applied to a wide range of learning and cognitive problems 33 – 45 , and (v) it provides strong robustness to noise—a key strength for IoT systems 46 . Despite the above-listed advantages, HDC encoding schemes are not designed for handling neuromorphic data.…”

Section: Introductionmentioning

confidence: 99%

Memory-inspired spiking hyperdimensional network for robust online learning

Zou

Alimohamadi

Zakeri

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Recently, brain-inspired computing models have shown great potential to outperform today’s deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (HDC) have shown promising results in enabling efficient and robust cognitive learning. Despite the success, these two brain-inspired models have different strengths. While SNN mimics the physical properties of the human brain, HDC models the brain on a more abstract and functional level. Their design philosophies demonstrate complementary patterns that motivate their combination. With the help of the classical psychological model on memory, we propose SpikeHD, the first framework that fundamentally combines Spiking neural network and hyperdimensional computing. SpikeHD generates a scalable and strong cognitive learning system that better mimics brain functionality. SpikeHD exploits spiking neural networks to extract low-level features by preserving the spatial and temporal correlation of raw event-based spike data. Then, it utilizes HDC to operate over SNN output by mapping the signal into high-dimensional space, learning the abstract information, and classifying the data. Our extensive evaluation on a set of benchmark classification problems shows that SpikeHD provides the following benefit compared to SNN architecture: (1) significantly enhance learning capability by exploiting two-stage information processing, (2) enables substantial robustness to noise and failure, and (3) reduces the network size and required parameters to learn complex information.

show abstract

GrapHD: Graph-Based Hyperdimensional Memorization for Brain-Like Cognitive Learning

Cited by 32 publications

References 64 publications

Hyperdimensional computing with holographic and adaptive encoder

Hyperdimensional computing with holographic and adaptive encoder

EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor

Memory-inspired spiking hyperdimensional network for robust online learning

Contact Info

Product

Resources

About