XL-HD: Extended Learning in Hyperdimensional Computing via Deterministic Projections for In-Memory Accelerators
For edge ML practitioners, XL-HD offers a fully learnable HDC method that is hardware-friendly for in-memory computing, though the accuracy gains over prior HDC are incremental.
XL-HD introduces a deterministic, projection-based hyperdimensional computing framework that achieves competitive accuracy on MNIST, UCIHAR, and ISOLET while enabling a compact in-memory accelerator with 0.395 mm² area and 0.40 μJ per inference.
Hyperdimensional computing (HDC) is a promising approach for energy-efficient edge machine learning (ML), where low latency, low power, and tight memory budgets are essential. However, traditional HDC relies on symbolic binding and pseudo-random high-dimensional vectors, which require large dimensionality and heuristic updates to reach competitive accuracy, limiting deployment on edge hardware. We introduce XL-HD, a deterministic, projection-based, fully learnable HDC framework tailored for in-memory acceleration within edge computing systems. The method uses a fixed Sobol sequence to project binary inputs, extending learning beyond conventional HDC. During training, class prototypes are optimized in real-valued space and later binarized, enabling an entirely binary dot-product inference pipeline ideal for IMC hardware such as ReRAM crossbars. XL-HD achieves competitive accuracy on MNIST, UCIHAR, and ISOLET while maintaining a compact IMC-based inference engine with $0.395 \ \text{mm}^2$ area and only $0.40 \ μ\text{J}$ per single-cycle inference.