让高维计算模型能反向传播训练，大幅降低维度要求
THDC: Training Hyperdimensional Computing Models with Backpropagation
- 用可训练嵌入替代随机高维向量，实现端到端学习
- 在多个数据集上达到或超过现有高维计算模型性能
- 维度从1万降至64，适合低功耗设备部署
高维计算（HDC）通过将数据编码为高维向量，在能源受限设备上实现轻量级学习。然而，其对超大维度和静态随机初始化的超向量依赖，限制了内存效率和学习能力。为此，我们提出可训练高维计算（THDC），支持通过反向传播进行端到端训练。THDC以可训练嵌入取代随机初始化向量，并引入一层二值神经网络优化类别表示。在MNIST、Fashion-MNIST和CIFAR-10上的评估显示，THDC在维度从10,000降至64的情况下，性能达到或优于当前最先进的HDC模型。
原文摘要 · Abstract (English)
Hyperdimensional computing (HDC) offers lightweight learning for energy-constrained devices by encoding data into high-dimensional vectors. However, its reliance on ultra-high dimensionality and static, randomly initialized hypervectors limits memory efficiency and learning capacity. Therefore, we propose Trainable Hyperdimensional Computing (THDC), which enables end-to-end HDC via backpropagation. THDC replaces randomly initialized vectors with trainable embeddings and introduces a one-layer binary neural network to optimize class representations. Evaluated on MNIST, Fashion-MNIST and CIFAR-10, THDC achieves equal or better accuracy than state-of-the-art HDC, with dimensionality reduced from 10.000 to 64.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。