DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification
This work addresses efficiency issues in HDC for resource-constrained devices, representing an incremental improvement over existing methods.
The paper tackles the problem of static encoders in hyperdimensional computing (HDC) requiring high dimensionality for accuracy, which reduces efficiency, and proposes DistHD, a dynamic encoding method that identifies and regenerates misleading dimensions to accelerate learning and achieve desired accuracy with lower dimensionality.
Brain-inspired hyperdimensional computing (HDC) has been recently considered a promising learning approach for resource-constrained devices. However, existing approaches use static encoders that are never updated during the learning process. Consequently, it requires a very high dimensionality to achieve adequate accuracy, severely lowering the encoding and training efficiency. In this paper, we propose DistHD, a novel dynamic encoding technique for HDC adaptive learning that effectively identifies and regenerates dimensions that mislead the classification and compromise the learning quality. Our proposed algorithm DistHD successfully accelerates the learning process and achieves the desired accuracy with considerably lower dimensionality.