2026-08-17 マサチューセッツ大学アマースト校
TetraMem’s MX100 kit was used for the hyperdimensional in-memory computing project led by Qiangfei Xia of UMass Amherst that was recently published in Nature Communications. Photo by Yi Huang, previously published in Nature Electronics.
＜関連情報＞
- https://www.umass.edu/news/article/umass-amherst-engineers-make-edge-ai-more-efficient-redesigning-both-algorithm-and
- https://www.nature.com/articles/s41467-026-76067-5
アナログ・メモリスティブ・クロスバーアレイを用いた超次元インメモリコンピューティング Hyperdimensional in-memory computing with analogue memristive crossbar arrays
Yi Huang,Alireza Jaberi Rad,Daniel Belkin,Ning Ge,J. Joshua Yang,Miao Hu & Qiangfei Xia
Nature Communications Published:28 July 2026
DOI:https://doi.org/10.1038/s41467-026-76067-5 Unedited version
Abstract
Deploying large-scale artificial intelligence models for language processing on edge devices is limited by constraints in computational capacity and energy efficiency. To address this challenge, we present a hardware-algorithm co-design framework that leverages analog in-memory computing and hyperdimensional computing for efficient language identification at the edge. By exploiting the inherent randomness and multistate properties of analog memristors, we implement a vector matrix multiplication-based language feature encoding with much reduced hardware complexity. Language classification is then realized with a single-layer perceptron on analog memristive crossbar arrays, eliminating inter-layer activation functions and backward propagation during training that are required in deep neural networks. Experimental implementation on a multicore memristive system-on-a-chip demonstrates a 90% reduction in hardware resources while achieving 95.24% language identification accuracy, the highest reported among hyperdimensional computing implementations on emerging hardware platforms. This work provides a scalable, energy-efficient approach for high-accuracy language processing on edge devices.
