skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, October 10 until 2:00 AM ET on Friday, October 11 due to maintenance. We apologize for the inconvenience.


Search for: All records

Award ID contains: 2312517

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Introduction

    Brain-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.

    Methods

    In 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.

    Results

    Our 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.

    Discussion

    The results indicate the importance of an adaptive encoder and customized high-dimensional representation in HDC.

     
    more » « less
    Free, publicly-accessible full text available April 9, 2025
  2. Abstract

    Although the connectivity offered by industrial internet of things (IIoT) enables enhanced operational capabilities, the exposure of systems to significant cybersecurity risks poses critical challenges. Recently, machine learning (ML) algorithms such as feature-based support vector machines and logistic regression, together with end-to-end deep neural networks, have been implemented to detect intrusions, including command injection, denial of service, reconnaissance, and backdoor attacks, by capturing anomalous patterns. However, ML algorithms not only fall short in agile identification of intrusion with few samples, but also fail in adapting to new data or environments. This paper introduces hyperdimensional computing (HDC) as a new cognitive computing paradigm that mimics brain functionality to detect intrusions in IIoT systems. HDC encodes real-time data into a high-dimensional representation, allowing for ultra-efficient learning and analysis with limited samples and a few passes. Additionally, we incorporate the concept of regenerating brain cells into hyperdimensional computing to further improve learning capability and reduce the required memory. Experimental results on the WUSTL-IIOT-2021 dataset show that HDC detects intrusion with the accuracy of 92.6%, which is superior to multi-layer perceptron (40.2%), support vector machine (72.9%), logistic regression (84.2%), and Gaussian process classification (89.1%) while requires only 300 data and 5 iterations for training.

     
    more » « less
  3. Free, publicly-accessible full text available July 1, 2025
  4. The 6G network, the next‐generation communication system, is envisaged to provide unprecedented experience through hyperconnectivity involving everything. The communication should hold artificial intelligence‐centric network infrastructures as interconnecting a swarm of machines. However, existing network systems use orthogonal modulation and costly error correction code; they are very sensitive to noise and rely on many processing layers. These schemes impose significant overhead on low‐power internet of things devices connected to noisy networks. Herein, a hyperdimensional network‐based system, called , is proposed, which enables robust and efficient data communication/learning. exploits a redundant and holographic representation of hyperdimensional computing (HDC) to design highly robust data modulation, enabling two functionalities on transmitted data: 1) an iterative decoding method that translates the vector back to the original data without error correction mechanisms, or 2) a native hyperdimensional learning technique on transmitted data with no need for costly data decoding. A hardware accelerator that supports both data decoding and hyperdimensional learning using a unified accelerator is also developed. The evaluation shows that provides a bit error rate comparable to that of state‐of‐the‐art modulation schemes while achieving 9.4 faster and 27.8 higher energy efficiency compared to state‐of‐the‐art deep learning systems.

     
    more » « less
    Free, publicly-accessible full text available July 1, 2025
  5. Free, publicly-accessible full text available June 17, 2025
  6. Free, publicly-accessible full text available June 12, 2025
  7. Deep random forest (DRF), which combines deep learning and random forest, exhibits comparable accuracy, interpretability, low memory and computational overhead to deep neural networks (DNNs) in edge intelligence tasks. However, efficient DRF accelerator is lagging behind its DNN counterparts. The key to DRF acceleration lies in realizing the branch-split operation at decision nodes. In this work, we propose implementing DRF through associative searches realized with ferroelectric analog content addressable memory (ACAM). Utilizing only two ferroelectric field effect transistors (FeFETs), the ultra-compact ACAM cell performs energy-efficient branch-split operations by storing decision boundaries as analog polarization states in FeFETs. The DRF accelerator architecture and its model mapping to ACAM arrays are presented. The functionality, characteristics, and scalability of the FeFET ACAM DRF and its robustness against FeFET device non-idealities are validated in experiments and simulations. Evaluations show that the FeFET ACAM DRF accelerator achieves ∼106×/10× and ∼106×/2.5× improvements in energy and latency, respectively, compared to other DRF hardware implementations on state-of-the-art CPU/ReRAM.

     
    more » « less
    Free, publicly-accessible full text available June 7, 2025
  8. Hyperdimensional computing (HDC) is a computing paradigm inspired by the mechanisms of human memory, characterizing data through high-dimensional vector representations, known as hypervectors. Recent advancements in HDC have explored its potential as a learning model, leveraging its straightforward arithmetic and high efficiency. The traditional HDC frameworks are hampered by two primary static elements: randomly generated encoders and fixed learning rates. These static components significantly limit model adaptability and accuracy. The static, randomly generated encoders, while ensuring high-dimensional representation, fail to adapt to evolving data relationships, thereby constraining the model’s ability to accurately capture and learn from complex patterns. Similarly, the fixed nature of the learning rate does not account for the varying needs of the training process over time, hindering efficient convergence and optimal performance. This paper introduces\(\mathsf {TrainableHD} \), a novel HDC framework that enables dynamic training of the randomly generated encoder depending on the feedback of the learning data, thereby addressing the static nature of conventional HDC encoders.\(\mathsf {TrainableHD} \)also enhances the training performance by incorporating adaptive optimizer algorithms in learning the hypervectors. We further refine\(\mathsf {TrainableHD} \)with effective quantization to enhance efficiency, allowing the execution of the inference phase in low-precision accelerators. Our evaluations demonstrate that\(\mathsf {TrainableHD} \)significantly improves HDC accuracy by up to 27.99% (averaging 7.02%) without additional computational costs during inference, achieving a performance level comparable to state-of-the-art deep learning models. Furthermore,\(\mathsf {TrainableHD} \)is optimized for execution speed and energy efficiency. Compared to deep learning on a low-power GPU platform like NVIDIA Jetson Xavier,\(\mathsf {TrainableHD} \)is 56.4 times faster and 73 times more energy efficient. This efficiency is further augmented through the use of Encoder Interval Training (EIT) and adaptive optimizer algorithms, enhancing the training process without compromising the model’s accuracy.

     
    more » « less
    Free, publicly-accessible full text available June 4, 2025
  9. Free, publicly-accessible full text available June 1, 2025
  10. Free, publicly-accessible full text available June 1, 2025