Torchhd: An Open-Source Python Library to Support Hyperdimensional Computing Research

Heddes, Mike; Nunes, Igor; Vergés, Pere; Desai, Dheyay; Givargis, Tony; Nicolau, Alexandru

doi:10.48550/arxiv.2205.09208

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Implementation: We use a Raspberry Pi 4 for data collection and HDC-based learning. We implement a novel HDC-based encoding based on the torch-hd [36] package. Each training epoch will go through sequential neural networks with one HDC encoding layer.…”

Section: Methodsmentioning

confidence: 99%

Enhanced Noise-Resilient Pressure Mat System Based on Hyperdimensional Computing

Asgarinejad,

Yu,

Jiang

et al. 2024

Sensors

View full text Add to dashboard Cite

Traditional systems for indoor pressure sensing and human activity recognition (HAR) rely on costly, high-resolution mats and computationally intensive neural network-based (NN-based) models that are prone to noise. In contrast, we design a cost-effective and noise-resilient pressure mat system for HAR, leveraging Velostat for intelligent pressure sensing and a novel hyperdimensional computing (HDC) classifier that is lightweight and highly noise resilient. To measure the performance of our system, we collected two datasets, capturing the static and continuous nature of human movements. Our HDC-based classification algorithm shows an accuracy of 93.19%, improving the accuracy by 9.47% over state-of-the-art CNNs, along with an 85% reduction in energy consumption. We propose a new HDC noise-resilient algorithm and analyze the performance of our proposed method in the presence of three different kinds of noise, including memory and communication, input, and sensor noise. Our system is more resilient across all three noise types. Specifically, in the presence of Gaussian noise, we achieve an accuracy of 92.15% (97.51% for static data), representing a 13.19% (8.77%) improvement compared to state-of-the-art CNNs.

show abstract

Section: Methodsmentioning

confidence: 99%

Enhanced Noise-Resilient Pressure Mat System Based on Hyperdimensional Computing

Asgarinejad,

Yu,

Jiang

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…In this paper, the seed hypervectors are either random hypervectors or level hypervectors: (i) random hypervectors are quasi-orthogonal to each other and are mainly employed to represent the independent categorical data, e.g., channel indices for biological signals; (ii) level hypervectors are usually linearly correlated and represent the sub-intervals of a given range, e.g., the quantized magnitude of a given time series. The reader is referred to [38,55] for more details. Record-based encoding [38]: This encoding algorithm typically requires two types of hypervectors, which contain the value and position information, respectively.…”

Section: A Traditional Clustering Algorithms 1) Traditional K-meansmentioning

confidence: 99%

“…We implement both HDCluster and our proposed HDC-based clustering algorithms using Python implementation. For hypervectors generation, we employ the library "torchhd" [55]. We evaluate the clustering algorithms by three metrics: accuracy (ground truth is known), number of iterations for the convergence of cluster hypervectors, and execution time.…”

Section: A Experimental Setupmentioning

confidence: 99%

Robust Clustering Using Hyperdimensional Computing

Ge,

Parhi

2024

IEEE Open J. Circuits Syst.

View full text Add to dashboard Cite

This paper addresses the clustering of data in the hyperdimensional computing (HDC) domain. In prior work, an HDC-based clustering framework, referred to as HDCluster, has been proposed. However, the performance of the existing HDCluster is not robust. The performance of HDCluster is degraded as the hypervectors for the clusters are chosen at random during the initialization step. To overcome this bottleneck, we assign the initial cluster hypervectors by exploring the similarity of the encoded data, referred to as query hypervectors. Intracluster hypervectors have a higher similarity than intercluster hypervectors. Harnessing the similarity results among query hypervectors, this paper proposes four HDCbased clustering algorithms: similarity-based k-means, equal bin-width histogram, equal bin-height histogram, and similarity-based affinity propagation. Experimental results illustrate that: (i) Compared to the existing HDCluster, our proposed HDC-based clustering algorithms can achieve better accuracy, more robust performance, fewer iterations, and less execution time. Similarity-based affinity propagation outperforms the other three HDC-based clustering algorithms on eight datasets by 2% ∼ 38% in clustering accuracy. (ii) Even for one-pass clustering, i.e., without any iterative update of the cluster hypervectors, our proposed algorithms can provide more robust clustering accuracy than HDCluster. (iii) Over eight datasets, five out of eight can achieve higher or comparable accuracy when projected onto the hyperdimensional space. Traditional clustering is more desirable than HDC when the number of clusters, k, is large.

show abstract

“…Despite the presence of a few existing libraries for building vector-symbolic architectures (Heddes et al, 2023;Kang et al, 2022;Simon et al, 2022), the development of hdlib was driven by the need to offer increased flexibility and a more intuitive interface to complex abstractions, thereby facilitating a wider adoption in the research community. It not only consolidates most of the features from the existing libraries but also introduces novel functionalities which are easily accessible through a set of abstractions and reusable components as described in the following section, enabling rapid prototyping and experimentation with various architectural configurations.…”

Section: Statement Of Needmentioning

confidence: 99%